├── CVer学术交流群.png ├── ECCV2020-Papers-with-Code.md ├── ECCV2022-Papers-with-Code.md └── README.md /CVer学术交流群.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/amusi/ECCV2024-Papers-with-Code/b3864f2e54221f3badf1d30b20919b3d71eedc8a/CVer学术交流群.png -------------------------------------------------------------------------------- /ECCV2020-Papers-with-Code.md: -------------------------------------------------------------------------------- 1 | # ECCV2020-Code 2 | ECCV 2020 论文开源项目合集，同时欢迎各位大佬提交issue，分享ECCV 2020开源项目 3 | 4 | 关于往年CV顶会论文（如CVPR 2020、ICCV 2019、ECCV 2018）以及其他优质CV论文和大盘点，详见： https://github.com/amusi/daily-paper-computer-vision 5 | 6 | - [CNN](#CNN) 7 | - [图像分类](#Image-Classification) 8 | - [2D目标检测](#Object-Detection) 9 | - [3D目标检测](#3D-Object-Detection) 10 | - [视频目标检测](#Video-Object-Detection) 11 | - [语义分割](#Semantic-Segmentation) 12 | - [实例分割](#Instance-Segmentation) 13 | - [全景分割](#Panoptic-Segmentation) 14 | - [视频目标分割](#VOS) 15 | - [单/多目标跟踪](#Object-Tracking) 16 | - [GAN](#GAN) 17 | - [NAS](#NAS) 18 | - [3D点云（分类/分割/配准/补全等）](#3D-PointCloud) 19 | - [人脸（检测/识别/解析等）](#Face) 20 | - [Re-ID](#Re-ID) 21 | - [显著性检测（SOD）](#Saliency) 22 | - [模型压缩（剪枝/知识蒸馏等）](#Model-Compression) 23 | - [视频理解/行为识别/行为检测](#Action-Recognition) 24 | - [场景文本检测](#Scene-Text-Detection) 25 | - [场景文本识别](#Scene-Text-Recognition) 26 | - [特征点检测/描述符/匹配](#Feature) 27 | - [姿态估计](#Pose-Estimation) 28 | - [深度估计](#Depth-Estimation) 29 | - [深度补全](#Depth-Completion) 30 | - [域泛化](#Domain-Generalization) 31 | - [超分辨率](#Super-Resolution) 32 | - [去模糊](#Deblurring) 33 | - [去雨](#Deraining) 34 | - [图像/视频恢复](#Image-Restoration) 35 | - [图像/视频修复(补全)](#Image-Video-Inpainting) 36 | - [风格迁移](#Style-Transfer) 37 | - [三维重建](#3D-Reconstruction) 38 | - [图像描述](#Image-Caption) 39 | - [图像检索](#Image-Retrieval) 40 | - [光流估计](#Optical-Flow-Estimation) 41 | - [视频插帧](#Video-Interpolation) 42 | - [车道线检测](#Lane-Detection) 43 | - [轨迹预测](#TP) 44 | - [线段检测](#Line-Detection) 45 | - [视线估计](#Gaze-Estimation) 46 | - [眼动追踪](#Eye-Tracking) 47 | - [对抗攻击](#Adversarial-Attack) 48 | - [数据集](#Datasets) 49 | - [其他](#Others) 50 | - [不确定中没中](#Not-Sure) 51 | 52 | 53 | 54 | # CNN 55 | 56 | **Beyond Fixed Grid: Learning Geometric Image Representation with a Deformable Grid** 57 | 58 | - 主页：http://www.cs.toronto.edu/~jungao/def-grid/ 59 | - 论文：http://xxx.itp.ac.cn/abs/2008.09269 60 | - 代码：https://github.com/fidler-lab/deformable-grid-release 61 | 62 | **WeightNet: Revisiting the Design Space of Weight Networks** 63 | 64 | - 论文：https://arxiv.org/abs/2007.11823 65 | - 代码：https://github.com/megvii-model/WeightNet 66 | 67 | **Feature Pyramid Transformer** 68 | 69 | - 论文：https://arxiv.org/abs/2007.09451 70 | 71 | - 代码：https://github.com/ZHANGDONG-NJUST/FPT 72 | 73 | **Dynamic Group Convolution for Accelerating Convolutional Neural Networks** 74 | 75 | - 论文：https://arxiv.org/abs/2007.04242 76 | - 代码：https://github.com/zhuogege1943/dgc 77 | 78 | **Learning to Learn Parameterized Classification Networks for Scalable Input Images** 79 | 80 | - 论文：https://arxiv.org/abs/2007.06181 81 | 82 | - 代码：https://github.com/d-li14/SAN 83 | 84 | **Rethinking Bottleneck Structure for Efficient Mobile Network Design** 85 | 86 | - 论文：https://arxiv.org/abs/2007.02269 87 | - 代码：https://github.com/zhoudaquan/rethinking_bottleneck_design 88 | 89 | **MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolution** 90 | 91 | - 论文：Oral 92 | - 论文：https://arxiv.org/abs/1909.12978 93 | - 代码：https://github.com/taoyang1122/MutualNet 94 | 95 | **PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer** 96 | 97 | - 论文：https://arxiv.org/abs/2007.06191 98 | - 代码：https://github.com/d-li14/PSConv 99 | 100 | 101 | 102 | # 图像分类 103 | 104 | **Learning to Learn Parameterized Classification Networks for Scalable Input Images** 105 | 106 | - 论文：暂无 107 | 108 | - 代码：https://github.com/d-li14/SAN 109 | 110 | **Learning To Classify Images Without Labels** 111 | 112 | - 论文：https://arxiv.org/abs/2005.12320 113 | - 代码：https://github.com/wvangansbeke/Unsupervised-Classification 114 | 115 | 116 | 117 | # 2D目标检测 118 | 119 | **Learning Data Augmentation Strategies for Object Detection** 120 | 121 | - 论文：https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/5865_ECCV_2020_paper.php 122 | - 代码：https://github.com/tensorflow/tpu/tree/master/models/official/detection 123 | 124 | **AABO: Adaptive Anchor Box Optimization for Object Detection via Bayesian Sub-sampling** 125 | 126 | - 论文：https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/3977_ECCV_2020_paper.php 127 | - 代码：https://github.com/wwdkl/AABO 128 | 129 | **Side-Aware Boundary Localization for More Precise Object Detection** 130 | 131 | - 论文：https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/2272_ECCV_2020_paper.php 132 | - 代码：https://github.com/open-mmlab/mmdetection 133 | 134 | **TIDE: A General Toolbox for Identifying Object Detection Errors** 135 | 136 | - 主页：https://dbolya.github.io/tide/ 137 | 138 | - 论文：https://arxiv.org/abs/2008.08115 139 | 140 | - 代码：https://github.com/dbolya/tide 141 | 142 | **Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector** 143 | 144 | - 主页：https://chengchunhsu.github.io/EveryPixelMatters/ 145 | - 论文：https://arxiv.org/abs/2008.08574 146 | - 代码：https://github.com/chengchunhsu/EveryPixelMatters 147 | 148 | **Dense RepPoints: Representing Visual Objects with Dense Point Sets** 149 | 150 | - 论文：https://arxiv.org/abs/1912.11473 151 | - 代码：https://github.com/justimyhxu/Dense-RepPoints 152 | 153 | **Corner Proposal Network for Anchor-free, Two-stage Object Detection** 154 | 155 | - 论文：https://arxiv.org/abs/2007.13816 156 | 157 | - 代码：https://github.com/Duankaiwen/CPNDet 158 | 159 | **BorderDet: Border Feature for Dense Object Detection** 160 | 161 | - 论文：https://arxiv.org/abs/2007.11056 162 | 163 | - 代码：https://github.com/Megvii-BaseDetection/BorderDet 164 | - 中文解读：https://zhuanlan.zhihu.com/p/163044323 165 | 166 | **Multi-Scale Positive Sample Refinement for Few-Shot Object Detection** 167 | 168 | - 论文：https://arxiv.org/abs/2007.09384 169 | 170 | - 代码：https://github.com/jiaxi-wu/MPSR 171 | 172 | **PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments** 173 | 174 | - 论文：https://arxiv.org/abs/2007.09584 175 | 176 | - 代码：https://github.com/clobotics/piou 177 | 178 | - 数据集：https://github.com/clobotics/piou 179 | 180 | **Probabilistic Anchor Assignment with IoU Prediction for Object Detection** 181 | 182 | - 论文：https://arxiv.org/abs/2007.08103 183 | - 代码：https://github.com/kkhoot/PAA 184 | 185 | **HoughNet: Integrating near and long-range evidence for bottom-up object detection** 186 | 187 | - 论文：https://arxiv.org/abs/2007.02355 188 | - 代码：https://github.com/nerminsamet/houghnet 189 | 190 | **OS2D: One-Stage One-Shot Object Detection by Matching Anchor Features** 191 | 192 | - 论文：https://arxiv.org/abs/2003.06800 193 | 194 | - 代码：https://github.com/aosokin/os2d 195 | 196 | **End-to-End Object Detection with Transformers** 197 | 198 | - Oral 199 | 200 | - 论文：https://ai.facebook.com/research/publications/end-to-end-object-detection-with-transformers 201 | - 代码：https://github.com/facebookresearch/detr 202 | 203 | **Dynamic R-CNN: Towards High Quality Object Detection via Dynamic Training** 204 | 205 | - 论文：https://arxiv.org/abs/2004.06002 206 | - 代码：https://github.com/hkzhang95/DynamicRCNN 207 | 208 | **OS2D: One-Stage One-Shot Object Detection by Matching Anchor Features** 209 | 210 | - 论文：https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/2424_ECCV_2020_paper.php 211 | - 代码：https://github.com/aosokin/os2d 212 | 213 | **Object Detection with a Unified Label Space from Multiple Datasets** 214 | 215 | - 主页：http://www.nec-labs.com/~mas/UniDet/ 216 | - 论文：https://arxiv.org/abs/2008.06614 217 | - 代码：暂无 218 | - 数据集：http://www.nec-labs.com/~mas/UniDet/resources/UOD_dataset_ECCV20.zip 219 | 220 | ### 弱监督目标检测 221 | 222 | **Enabling Deep Residual Networks for Weakly Supervised Object Detection** 223 | 224 | - 论文：https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/479_ECCV_2020_paper.php 225 | - 代码：https://github.com/shenyunhang/DRN-WSOD 226 | 227 | **UFO²: A Unified Framework towards Omni-supervised Object Detection** 228 | 229 | - 论文：https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/3205_ECCV_2020_paper.php 230 | - 代码：https://github.com/NVlabs/wetectron 231 | 232 | **Boosting Weakly Supervised Object Detection with Progressive Knowledge Transfer** 233 | 234 | - 论文：https://arxiv.org/abs/2007.07986 235 | - 代码：https://github.com/mikuhatsune/wsod_transfer 236 | 237 | ### 域自适应目标检测 238 | 239 | **Collaborative Training between Region Proposal Localization and Classification for Domain Adaptive Object Detection** 240 | 241 | - 论文：https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/2920_ECCV_2020_paper.php 242 | - 代码：https://github.com/GanlongZhao/CST_DA_detection 243 | 244 | **Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector** 245 | 246 | - 主页：https://chengchunhsu.github.io/EveryPixelMatters/ 247 | - 论文：https://arxiv.org/abs/2008.08574 248 | - 代码：https://github.com/chengchunhsu/EveryPixelMatters 249 | 250 | ### Few-Shot 目标检测 251 | 252 | **Multi-Scale Positive Sample Refinement for Few-Shot Object Detection** 253 | 254 | - 论文：https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/2581_ECCV_2020_paper.php 255 | - 代码：https://github.com/jiaxi-wu/MPSR 256 | 257 | ### 水下目标检测 258 | 259 | **Dual Refinement Underwater Object Detection Network** 260 | 261 | - 论文：https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/3425_ECCV_2020_paper.php 262 | - 代码：https://github.com/Peterchen111/FERNet 263 | 264 | ## 遥感旋转目标检测 265 | 266 | **PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments** 267 | 268 | - 论文：https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/3087_ECCV_2020_paper.php 269 | - 代码：https://github.com/clobotics/piou 270 | - 数据集：https://github.com/clobotics/piou 271 | 272 | **Arbitrary-Oriented Object Detection with Circular Smooth Label** 273 | 274 | - 论文：https://arxiv.org/abs/2003.05597 275 | - 代码：https://github.com/Thinklab-SJTU/CSL_RetinaNet_Tensorflow 276 | 277 | 278 | 279 | # 3D目标检测 280 | 281 | **Rethinking Pseudo-LiDAR Representation** 282 | 283 | - 论文：https://arxiv.org/abs/2008.04582 284 | 285 | - 代码：https://github.com/xinzhuma/patchnet 286 | 287 | **Pillar-based Object Detection for Autonomous Driving** 288 | 289 | - 论文：https://arxiv.org/abs/2007.10323 290 | - 代码：https://github.com/WangYueFt/pillar-od 291 | 292 | **EPNet: Enhancing Point Features with Image Semantics for 3D Object Detection** 293 | 294 | - 论文：https://arxiv.org/abs/2007.08856 295 | - 代码：https://github.com/happinesslz/EPNet 296 | 297 | 298 | 299 | # 视频目标检测 300 | 301 | **Mining Inter-Video Proposal Relations for Video Object Detection** 302 | 303 | - 论文：https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/3764_ECCV_2020_paper.php 304 | - 代码：https://github.com/youthHan/HVRNet 305 | 306 | **Learning Where to Focus for Efficient Video Object Detection** 307 | 308 | - 主页：https://jiangzhengkai.github.io/LSTS/ 309 | - 论文：https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123610018.pdf 310 | - 代码：https://github.com/jiangzhengkai/LSTS 311 | 312 | 313 | 314 | # 语义分割 315 | 316 | **SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection** 317 | 318 | - 主页：https://sites.google.com/view/sne-roadseg 319 | - 论文：https://arxiv.org/abs/2008.11351 320 | - 代码：https://github.com/hlwang1124/SNE-RoadSeg 321 | - 数据集：https://drive.google.com/file/d/1YnkqPmzxtjNfMi2B1gMy7LQa5Gnu-BsH/view 322 | 323 | **Tensor Low-Rank Reconstruction for Semantic Segmentation** 324 | 325 | - 论文：https://arxiv.org/abs/2008.00490 326 | 327 | - 代码：https://github.com/CWanli/RecoNet 328 | 329 | **Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation** 330 | 331 | - 论文：https://arxiv.org/abs/2007.09183 332 | 333 | - 代码：https://github.com/charlesCXK/RGBD_Semantic_Segmentation_PyTorch 334 | 335 | **GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild** 336 | 337 | - 主页：https://lttm.dei.unipd.it/paper_data/GMNet/ 338 | - 论文：https://arxiv.org/abs/2007.09073 339 | - 代码：https://github.com/LTTM/GMNet 340 | 341 | **SegFix: Model-Agnostic Boundary Refinement for Segmentation** 342 | 343 | - 论文：https://arxiv.org/abs/2007.04269 344 | 345 | - 代码：https://github.com/openseg-group/openseg.pytorch 346 | 347 | **Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation** 348 | 349 | - Oral 350 | - 论文：https://arxiv.org/abs/2007.01947 351 | - 代码：https://github.com/GuoleiSun/MCIS_wsss 352 | 353 | **Improving Semantic Segmentation via Decoupled Body and Edge Supervision** 354 | 355 | - 论文：https://arxiv.org/abs/2007.10035 356 | 357 | - 代码：https://github.com/lxtGH/DecoupleSegNets 358 | 359 | 360 | 361 | # 实例分割 362 | 363 | **SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation** 364 | 365 | - 论文：https://arxiv.org/abs/2007.14772 366 | 367 | - 代码：https://github.com/JialeCao001/SipMask 368 | 369 | **Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation** 370 | 371 | - 论文：https://arxiv.org/abs/2007.12387 372 | 373 | - 代码：https://github.com/fanq15/CPMask 374 | 375 | **Boundary-preserving Mask R-CNN** 376 | 377 | - 论文：https://arxiv.org/abs/2007.08921 378 | 379 | - 代码：https://github.com/hustvl/BMaskR-CNN 380 | 381 | **Conditional Convolutions for Instance Segmentation** 382 | 383 | - Oral 384 | - 论文：https://arxiv.org/abs/2003.05664 385 | - 代码：https://github.com/aim-uofa/AdelaiDet/blob/master/configs/CondInst/README.md 386 | 387 | **SOLO: Segmenting Objects by Locations** 388 | 389 | - 论文：https://arxiv.org/abs/1912.04488 390 | - 代码：https://github.com/WXinlong/SOLO 391 | 392 | - 知乎话题：https://www.zhihu.com/question/360594484 393 | 394 | 395 | 396 | # 全景分割 397 | 398 | **Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic Segmentation** 399 | 400 | - 论文：https://arxiv.org/abs/2003.07853 401 | 402 | - 代码：https://github.com/csrhddlam/axial-deeplab 403 | - 视频：https://youtu.be/-iAXF-vibdE 404 | 405 | 406 | 407 | # 视频目标分割 408 | 409 | **Collaborative Video Object Segmentation by Foreground-Background Integration** 410 | 411 | - 论文：https://arxiv.org/abs/2003.08333 412 | - 代码：https://github.com/z-x-yang/CFBI 413 | 414 | **Video Object Segmentation with Episodic Graph Memory Networks** 415 | 416 | - 论文：https://arxiv.org/abs/2007.07020 417 | 418 | - 代码：https://github.com/carrierlxk/GraphMemVOS 419 | 420 | 421 | 422 | # 单/多目标跟踪 423 | 424 | **Ocean: Object-aware Anchor-Free Tracking** 425 | 426 | - 论文：https://arxiv.org/abs/2006.10721 427 | 428 | - 代码：https://github.com/researchmm/TracKit 429 | 430 | ## 多目标跟踪 431 | 432 | **Towards Real-Time Multi-Object Tracking** 433 | 434 | - 论文：暂无 435 | - 代码：https://github.com/Zhongdao/Towards-Realtime-MOT 436 | 437 | **Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking** 438 | 439 | - 论文：https://arxiv.org/abs/2008.08826 440 | - 代码：https://github.com/shijieS/DMMN 441 | - 数据集：https://github.com/shijieS/OmniMOTDataset 442 | 443 | **Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Tracking** 444 | 445 | - 论文：https://arxiv.org/abs/2007.14557 446 | 447 | - 代码：https://github.com/pjl1995/CTracker 448 | 449 | **Ocean: Object-aware Anchor-Free Tracking** 450 | 451 | - 论文：https://arxiv.org/abs/2006.10721 452 | 453 | - 代码：https://github.com/researchmm/TracKit 454 | 455 | **TAO: A Large-Scale Benchmark for Tracking Any Object** 456 | 457 | - 主页：http://taodataset.org/ 458 | - 论文：https://arxiv.org/abs/2005.10356 459 | - 代码：https://github.com/TAO-Dataset/tao 460 | 461 | **Segment as Points for Efficient Online Multi-Object Tracking and Segmentation** 462 | 463 | - Oral 464 | - 论文：https://arxiv.org/abs/2007.01550 465 | - 代码：https://github.com/detectRecog/PointTrack 466 | - 数据集：https://github.com/detectRecog/PointTrack 467 | 468 | 469 | 470 | # GAN 471 | 472 | **Rewriting a Deep Generative Model** 473 | 474 | - 论文：https://arxiv.org/abs/2007.15646 475 | 476 | - 代码：https://github.com/davidbau/rewriting 477 | 478 | **Contrastive Learning for Unpaired Image-to-Image Translation** 479 | 480 | - 论文：https://arxiv.org/abs/2007.15651 481 | - 代码：https://github.com/taesungp/contrastive-unpaired-translation 482 | 483 | **XingGAN for Person Image Generation** 484 | 485 | - 论文：暂无 486 | - 代码：https://github.com/Ha0Tang/XingGAN 487 | 488 | 489 | 490 | # NAS 491 | 492 | **Are Labels Necessary for Neural Architecture Search?** 493 | 494 | - 论文：https://arxiv.org/abs/2003.12056 495 | 496 | - 代码：https://github.com/facebookresearch/unnas 497 | 498 | **Rethinking Bottleneck Structure for Efficient Mobile Network Design** 499 | 500 | - 论文：https://arxiv.org/abs/2007.02269 501 | - 代码：https://github.com/zhoudaquan/rethinking_bottleneck_design 502 | 503 | **Fair DARTS: Eliminating Unfair Advantages in Differentiable Architecture Search** 504 | 505 | - 论文：https://arxiv.org/abs/1911.12126 506 | - 代码：https://github.com/xiaomi-automl/fairdarts 507 | 508 | 509 | 510 | # 3D点云（分类/分割/配准/补全等） 511 | 512 | **AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds** 513 | 514 | - 论文：https://arxiv.org/abs/1912.00461 515 | 516 | - 代码：https://github.com/ajhamdi/AdvPC 517 | 518 | **A Closer Look at Local Aggregation Operators in Point Cloud Analysis** 519 | 520 | - 论文：https://arxiv.org/abs/2007.01294 521 | - 代码：https://github.com/zeliu98/CloserLook3D 522 | 523 | ## 3D点云补全 524 | 525 | **Multimodal Shape Completion via Conditional Generative Adversarial Networks** 526 | 527 | - 论文：https://arxiv.org/abs/2003.07717 528 | - 代码：https://github.com/ChrisWu1997/Multimodal-Shape-Completion 529 | 530 | **GRNet: Gridding Residual Network for Dense Point Cloud Completion** 531 | 532 | - 论文：https://arxiv.org/abs/2006.03761 533 | - 代码：https://github.com/hzxie/GRNet 534 | 535 | ## 3D点云生成 536 | 537 | **Progressive Point Cloud Deconvolution Generation Network** 538 | 539 | - 论文：https://arxiv.org/abs/2007.05361 540 | 541 | - 代码：https://github.com/fpthink/PDGN 542 | 543 | 544 | 545 | # 人脸（检测/识别/解析等） 546 | 547 | ## 人脸检测 548 | 549 | **ProgressFace: Scale-Aware Progressive Learning for Face Detection** 550 | 551 | - 论文：http://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123510341.pdf 552 | - 代码：https://github.com/jiashu-zhu/ProgressFace 553 | 554 | ## 人脸识别 555 | 556 | **Explainable Face Recognition** 557 | 558 | - 论文：https://arxiv.org/abs/2008.00916 559 | 560 | - 主页：https://stresearch.github.io/xfr/ 561 | - 代码：https://github.com/stresearch/xfr 562 | 563 | ## 3D人脸重建 564 | 565 | **Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency** 566 | 567 | - 论文：https://arxiv.org/abs/2007.12494 568 | - 代码：https://github.com/jiaxiangshang/MGCNet 569 | 570 | ## 人脸活体检测 571 | 572 | **CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations** 573 | 574 | - 论文：https://arxiv.org/abs/2007.12342 575 | 576 | - 数据集：https://github.com/Davidzhangyuanhan/CelebA-Spoof 577 | 578 | ## 人脸解析 579 | 580 | **Edge-aware Graph Representation Learning and Reasoning for Face Parsing** 581 | 582 | - 论文：https://arxiv.org/abs/2007.11240 583 | - 代码：https://github.com/tegusi/EAGRNet 584 | 585 | ## DeepFakes 586 | 587 | **What makes fake images detectable? Understanding properties that generalize** 588 | 589 | - 主页：https://chail.github.io/patch-forensics/ 590 | - 论文：http://xxx.itp.ac.cn/abs/2008.10588 591 | - 代码：https://github.com/chail/patch-forensics 592 | 593 | ## 其他 594 | 595 | **Lifespan Age Transformation Synthesis** 596 | 597 | - 论文：https://arxiv.org/abs/2003.09764 598 | - 代码：https://github.com/royorel/Lifespan_Age_Transformation_Synthesis 599 | 600 | 601 | 602 | # Re-ID 603 | 604 | ## 行人重识别 605 | 606 | **Rethinking the Distribution Gap of Person Re-identification with Camera-based Batch Normalization** 607 | 608 | - 论文：https://arxiv.org/abs/2001.08680 609 | - 代码：https://github.com/automan000/Camera-based-Person-ReID 610 | 611 | **Appearance-Preserving 3D Convolution for Video-based Person Re-identification** 612 | 613 | - Oral 614 | 615 | - 论文：https://arxiv.org/pdf/2007.08434 616 | - 代码：https://github.com/guxinqian/AP3D 617 | 618 | **Do Not Disturb Me: Person Re-identification Under the Interference of Other Pedestrians** 619 | 620 | - 论文：https://arxiv.org/abs/2008.06963 621 | - 代码：https://github.com/X-BrainLab/PI-ReID 622 | 623 | **Faster Person Re-Identification** 624 | 625 | - 论文：https://arxiv.org/abs/2008.06826 626 | 627 | - 代码：https://github.com/wangguanan/light-reid 628 | 629 | **Temporal Complementary Learning for Video Person Re-Identification** 630 | 631 | - 论文：https://arxiv.org/abs/2007.09357 632 | 633 | - 代码：https://github.com/blue-blue272/VideoReID-TCLNet 634 | 635 | **Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification** 636 | 637 | - 论文：https://arxiv.org/abs/2007.10315 638 | - 代码：https://github.com/NVlabs/DG-Net-PP 639 | 640 | **Robust Re-Identification by Multiple Views Knowledge Distillation** 641 | 642 | - 论文：https://arxiv.org/abs/2007.04174 643 | - 代码：https://github.com/aimagelab/VKD 644 | 645 | **Multiple Expert Brainstorming for Domain Adaptive Person Re-identification** 646 | 647 | - 论文：https://arxiv.org/abs/2007.01546 648 | - 代码：https://github.com/YunpengZhai/MEB-Net 649 | 650 | ## 车辆重识别 651 | 652 | **Simulating Content Consistent Vehicle Datasets with Attribute Descent** 653 | 654 | - 论文：https://arxiv.org/abs/1912.08855 655 | - 代码：https://github.com/yorkeyao/VehicleX 656 | - 数据集：https://github.com/yorkeyao/VehicleX 657 | 658 | **Orientation-aware Vehicle Re-identification with Semantics-guided Part Attention Network** 659 | 660 | - 主页：http://media.ee.ntu.edu.tw/research/SPAN/ 661 | 662 | - 论文：https://arxiv.org/abs/2008.11423 663 | - 代码：https://github.com/tsaishien-chen/SPAN 664 | 665 | 666 | 667 | # 显著性检测（SOD） 668 | 669 | **Progressively Guided Alternate Refinement Network for RGB-D Salient Object Detection** 670 | 671 | - 论文：http://xxx.itp.ac.cn/abs/2008.07064 672 | 673 | - 代码：https://github.com/ShuhanChen/PGAR_ECCV20 674 | 675 | **Suppress and Balance: A Simple Gated Network for Salient Object Detection** 676 | 677 | - Oral 678 | 679 | - 论文：https://arxiv.org/abs/2007.08074 680 | - 代码：https://github.com/Xiaoqi-Zhao-DLUT/GateNet-RGB-Saliency 681 | 682 | **Hierarchical Dynamic Filtering Network for RGB-D Salient Object Detection** 683 | 684 | - 论文：https://arxiv.org/abs/2007.06227 685 | 686 | - 代码：https://github.com/lartpang/HDFNet 687 | 688 | **A Single Stream Network for Robust and Real-time RGB-D Salient Object Detection** 689 | 690 | - 论文：https://arxiv.org/abs/2007.06811 691 | - 代码：https://github.com/Xiaoqi-Zhao-DLUT/DANet-RGBD-Saliency 692 | 693 | **Cross-Modal Weighting Network for RGB-D Salient Object Detection** 694 | 695 | - 论文：暂无 696 | 697 | - 代码：https://github.com/MathLee/CMWNet 698 | 699 | **BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network** 700 | 701 | - 论文：暂无 702 | - 代码：https://github.com/DengPingFan/BBS-Net 703 | 704 | **Highly Efficient Salient Object Detection with 100K Parameters** 705 | 706 | - 论文：https://arxiv.org/abs/2003.05643 707 | - 代码：https://github.com/MCG-NKU/Sal100K 708 | 709 | 710 | 711 | # 模型压缩（剪枝/知识蒸馏等） 712 | 713 | **EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning** 714 | 715 | - 论文：https://arxiv.org/abs/2007.02491 716 | - 代码：https://github.com/anonymous47823493/EagleEye 717 | 718 | 719 | 720 | # 视频理解/行为识别/行为检测 721 | 722 | **AssembleNet++: Assembling Modality Representations via Attention Connections** 723 | 724 | - 论文：https://arxiv.org/abs/2008.08072 725 | - 代码：https://sites.google.com/corp/view/assemblenet/ 726 | 727 | **LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities** 728 | 729 | - 主页：https://sites.google.com/view/lemma-activity 730 | 731 | - 论文：https://arxiv.org/abs/2007.15781 732 | 733 | - 数据集：https://sites.google.com/view/lemma-activity/home/dataset 734 | - 代码：https://github.com/Buzz-Beater/LEMMA 735 | 736 | **AR-Net: Adaptive Frame Resolution for Efficient Action Recognition** 737 | 738 | - 主页：https://mengyuest.github.io/AR-Net/ 739 | - 论文：https://arxiv.org/abs/2007.15796 740 | - 代码：https://github.com/mengyuest/AR-Net 741 | 742 | **Context-Aware RCNN: A Baseline for Action Detection in Videos** 743 | 744 | - 论文：https://arxiv.org/abs/2007.09861 745 | 746 | - 代码：https://github.com/MCG-NJU/CRCNN-Action 747 | 748 | **Actions as Moving Points** 749 | 750 | - 论文：https://arxiv.org/abs/2001.04608 751 | - 代码：https://github.com/MCG-NJU/MOC-Detector 752 | 753 | **SF-Net: Single-Frame Supervision for Temporal Action Localization** 754 | 755 | - 论文：https://arxiv.org/abs/2003.06845 756 | - 代码：https://github.com/Flowerfan/SF-Net 757 | 758 | **Asynchronous Interaction Aggregation for Action Detection** 759 | 760 | - 论文：https://arxiv.org/abs/2004.07485 761 | 762 | - 代码：https://github.com/MVIG-SJTU/AlphAction 763 | 764 | 765 | 766 | # 场景文本检测 767 | 768 | **Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting** 769 | 770 | - 论文：https://arxiv.org/abs/2007.09482 771 | 772 | - 代码：https://github.com/MhLiao/MaskTextSpotterV3 773 | 774 | 775 | 776 | # 场景文本识别 777 | 778 | **Adaptive Text Recognition through Visual Matching** 779 | 780 | - 主页：http://www.robots.ox.ac.uk/~vgg/research/FontAdaptor20/ 781 | 782 | - 论文：https://arxiv.org/abs/2009.06610 783 | 784 | - 代码：https://github.com/Chuhanxx/FontAdaptor 785 | 786 | **Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting** 787 | 788 | - 论文：https://arxiv.org/abs/2007.09482 789 | 790 | - 代码：https://github.com/MhLiao/MaskTextSpotterV3 791 | 792 | 793 | 794 | # 特征点检测/描述符/匹配 795 | 796 | **Learning and aggregating deep local descriptors for instance-level recognition** 797 | 798 | - 论文：https://arxiv.org/abs/2007.13172 799 | 800 | - 代码：https://github.com/gtolias/how 801 | 802 | **Online Invariance Selection for Local Feature Descriptors** 803 | 804 | - Oral 805 | - 论文：https://arxiv.org/abs/2007.08988 806 | - 代码：https://github.com/rpautrat/LISRD 807 | 808 | **Single-Image Depth Prediction Makes Feature Matching Easier** 809 | 810 | - 论文：https://arxiv.org/abs/2008.09497 811 | 812 | - 代码：http://www.github.com/nianticlabs/rectified-features 813 | 814 | 815 | 816 | # 姿态估计 817 | 818 | **Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose** 819 | 820 | - 论文：https://arxiv.org/abs/2008.09047 821 | - 代码：https://github.com/hongsukchoi/Pose2Mesh_RELEASE 822 | 823 | **Key Frame Proposal Network for Efficient Pose Estimation in Videos** 824 | 825 | - 论文：https://arxiv.org/abs/2007.15217 826 | - 代码：https://github.com/Yuexiaoxi10/Key-Frame-Proposal-Network-for-Efficient-Pose-Estimation-in-Videos 827 | 828 | ## 3D人体姿态估计 829 | 830 | **DOPE: Distillation Of Part Experts for whole-body 3D pose estimation in the wild** 831 | 832 | - 主页：https://europe.naverlabs.com/blog/dope-distillation-of-part-experts-for-whole-body-3d-pose-estimation-in-the-wild/ 833 | 834 | - 论文：https://arxiv.org/abs/2008.09457 835 | 836 | - 代码：https://github.com/naver/dope 837 | 838 | 839 | **SMAP: Single-Shot Multi-Person Absolute 3D Pose Estimation** 840 | 841 | - 主页：https://zju3dv.github.io/SMAP/ 842 | - 论文：https://arxiv.org/abs/2008.11469 843 | - 代码：https://github.com/zju3dv/SMAP 844 | 845 | ## 6D位姿估计 846 | 847 | **CosyPose: Consistent multi-view multi-object 6D pose estimation** 848 | 849 | - 主页：https://www.di.ens.fr/willow/research/cosypose/ 850 | 851 | - 论文：http://xxx.itp.ac.cn/abs/2008.08465 852 | 853 | - 代码：https://github.com/ylabbe/cosypose 854 | 855 | 856 | 857 | # 深度估计 858 | 859 | **Learning Stereo from Single Images** 860 | 861 | - 论文：https://arxiv.org/abs/2008.01484 862 | - 代码：https://github.com/nianticlabs/stereo-from-mono/ 863 | 864 | ## 单目深度估计 865 | 866 | **P2Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation** 867 | 868 | - 论文：https://arxiv.org/abs/2007.07696 869 | - 代码：https://github.com/svip-lab/Indoor-SfMLearner 870 | 871 | **Self-Supervised Monocular Depth Estimation: Solving the Dynamic Object Problem by Semantic Guidance** 872 | 873 | - 论文：https://arxiv.org/abs/2007.06936 874 | 875 | - 代码：https://github.com/ifnspaml/SGDepth 876 | 877 | 878 | 879 | # 深度补全 880 | 881 | **Non-Local Spatial Propagation Network for Depth Completion** 882 | 883 | - 论文：https://arxiv.org/abs/2007.10042 884 | - 代码：https://github.com/zzangjinsun/NLSPN_ECCV20 885 | 886 | 887 | 888 | # 域泛化 889 | 890 | **Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization** 891 | 892 | - 论文：https://arxiv.org/abs/2007.09316 893 | - 代码：https://github.com/EmmaW8/EISNet 894 | 895 | 896 | 897 | # 超分辨率 898 | 899 | ## 图像超分辨率 900 | 901 | **Learning the Super-Resolution Space with Normalizing Flow** 902 | 903 | - 论文：https://arxiv.org/abs/2006.14200 904 | - 代码：https://github.com/andreas128/SRFlow 905 | 906 | **Deep Decomposition Learning for Inverse Imaging Problems** 907 | 908 | - 论文：https://arxiv.org/abs/1911.11028 909 | - 代码：https://github.com/edongdongchen/DDN 910 | 911 | **Component Divide-and-Conquer for Real-World Image Super-Resolution** 912 | 913 | - 论文：https://arxiv.org/abs/2008.01928 914 | - 代码：https://github.com/xiezw5/Component-Divide-and-Conquer-for-Real-World-Image-Super-Resolution 915 | - 数据集：https://github.com/xiezw5/Component-Divide-and-Conquer-for-Real-World-Image-Super-Resolution 916 | 917 | **Learning with Privileged Information for Efficient Image Super-Resolution** 918 | 919 | - 主页：https://cvlab.yonsei.ac.kr/projects/PISR/ 920 | - 论文：https://arxiv.org/abs/2007.07524 921 | - 代码：https://github.com/cvlab-yonsei/PISR 922 | 923 | **Spatial-Angular Interaction for Light Field Image Super-Resolution** 924 | 925 | - 论文：https://arxiv.org/abs/1912.07849 926 | - 代码：https://github.com/YingqianWang/LF-InterNet 927 | 928 | **Invertible Image Rescaling** 929 | 930 | - 论文：https://arxiv.org/abs/2005.05650 931 | - 代码：https://github.com/pkuxmq/Invertible-Image-Rescaling 932 | 933 | ## 视频超分辨率 934 | 935 | **Video Super-Resolution with Recurrent Structure-Detail Network** 936 | 937 | - 论文：https://arxiv.org/abs/2008.00455 938 | 939 | - 代码：https://github.com/junpan19/RSDN 940 | 941 | 942 | 943 | # 去模糊 944 | 945 | ## 图像去模糊 946 | 947 | **End-to-end Interpretable Learning of Non-blind Image Deblurring** 948 | 949 | - 论文：https://arxiv.org/abs/2007.01769 950 | - 代码：暂无（即将出来） 951 | 952 | ## 视频去模糊 953 | 954 | **Efficient Spatio-Temporal Recurrent Neural Network for Video Deblurring** 955 | 956 | - 论文：https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/5116_ECCV_2020_paper.php 957 | - 代码：https://github.com/zzh-tech/ESTRNN 958 | 959 | 960 | 961 | # 去雨 962 | 963 | **Rethinking Image Deraining via Rain Streaks and Vapors** 964 | 965 | - 论文：https://arxiv.org/abs/2008.00823 966 | - 代码：https://github.com/yluestc/derain 967 | 968 | 969 | 970 | # 图像/视频恢复 971 | 972 | **Learning Enriched Features for Real Image Restoration and Enhancement** 973 | 974 | - 论文：https://arxiv.org/abs/2003.06792 975 | - 代码：https://github.com/swz30/MIRNet 976 | 977 | 978 | 979 | # 图像/视频修复(补全) 980 | 981 | **NAS-DIP: Learning Deep Image Prior with Neural Architecture Search** 982 | 983 | - 主页：https://yunchunchen.github.io/NAS-DIP/ 984 | - 论文：https://arxiv.org/abs/2008.11713 985 | - 代码：https://github.com/YunChunChen/NAS-DIP-pytorch 986 | 987 | **Learning Joint Spatial-Temporal Transformations for Video Inpainting** 988 | 989 | - 论文：https://arxiv.org/abs/2007.10247 990 | 991 | - 代码：https://github.com/researchmm/STTN 992 | 993 | **Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations** 994 | 995 | - Oral 996 | - 论文：暂无 997 | - 代码：https://github.com/KumapowerLIU/ECCV2020oralRethinking-Image-Inpainting-via-a-Mutual-Encoder-Decoder-with-Feature-Equalizations 998 | 999 | 1000 | 1001 | # 风格迁移 1002 | 1003 | **Domain-Specific Mappings for Generative Adversarial Style Transfer** 1004 | 1005 | - 主页：https://acht7111020.github.io/DSMAP-demo/ 1006 | - 论文：http://xxx.itp.ac.cn/abs/2008.02198 1007 | - 代码：https://github.com/acht7111020/DSMAP 1008 | 1009 | 1010 | 1011 | # 三维重建 1012 | 1013 | **Atlas: End-to-End 3D Scene Reconstruction from Posed Images** 1014 | 1015 | - 主页：http://zak.murez.com/atlas/ 1016 | - 论文：https://arxiv.org/abs/2003.10432 1017 | - 代码：https://github.com/magicleap/Atlas 1018 | - 视频：https://youtu.be/9NOPcOGV6nU 1019 | 1020 | **3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View** 1021 | 1022 | - 主页：https://marcbadger.github.io/avian-mesh/ 1023 | - 论文：https://arxiv.org/abs/2008.06133 1024 | - 代码：https://github.com/marcbadger/avian-mesh 1025 | - 数据集：https://drive.google.com/file/d/1vyXYIJIo9jneIqC7lowB4GVi17rjztjn/view?usp=sharing 1026 | 1027 | **Stochastic Bundle Adjustment for Efficient and Scalable 3D Reconstruction** 1028 | 1029 | - 论文：http://xxx.itp.ac.cn/abs/2008.00446 1030 | 1031 | - 代码：https://github.com/zlthinker/STBA 1032 | 1033 | 1034 | 1035 | # 图像描述 1036 | 1037 | **Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards** 1038 | 1039 | - 论文：https://arxiv.org/abs/2008.02693 1040 | 1041 | - 代码： https://github.com/xuewyang/Fashion_Captioning 1042 | - 数据集：https://drive.google.com/drive/folders/1J6SZOt_WFwZToX1Jf7QiXzFVwt23lGwW?usp=sharing 1043 | 1044 | 1045 | 1046 | # 图像检索 1047 | 1048 | **SOLAR: Second-Order Loss and Attention for Image Retrieval** 1049 | 1050 | - 论文：https://arxiv.org/abs/2001.08972 1051 | 1052 | - 代码：https://github.com/tonyngjichun/SOLAR 1053 | 1054 | **Self-supervising Fine-grained Region Similarities for Large-scale Image Localization** 1055 | 1056 | - 主页：https://yxgeee.github.io/projects/sfrs 1057 | - 论文：https://arxiv.org/abs/2006.03926 1058 | 1059 | - 代码：https://github.com/yxgeee/SFRS 1060 | 1061 | 1062 | 1063 | # 光流估计 1064 | 1065 | **RAFT: Recurrent All-Pairs Field Transforms for Optical Flow** 1066 | 1067 | - 论文：https://arxiv.org/abs/2003.12039 1068 | 1069 | - 代码：https://github.com/princeton-vl/RAFT 1070 | 1071 | **LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation** 1072 | 1073 | - 论文：https://arxiv.org/abs/2007.09319 1074 | - 代码：https://github.com/twhui/LiteFlowNet3 1075 | 1076 | 1077 | 1078 | # 视频插帧 1079 | 1080 | **BMBC: Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation** 1081 | 1082 | - 论文：https://arxiv.org/abs/2007.12622 1083 | 1084 | - 代码：https://github.com/JunHeum/BMBC 1085 | 1086 | 1087 | 1088 | # 车道线检测 1089 | 1090 | **CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending** 1091 | 1092 | - 论文：https://arxiv.org/abs/2007.12147 1093 | - 数据集：https://github.com/xbjxh/curvelanes 1094 | 1095 | **Ultra Fast Structure-aware Deep Lane Detection** 1096 | 1097 | - 论文：https://arxiv.org/abs/2004.11757 1098 | 1099 | - 代码：https://github.com/cfzd/Ultra-Fast-Lane-Detection 1100 | - 论文解读：https://mp.weixin.qq.com/s/TYzDx8R1oUbVr0FxGnFspQ 1101 | 1102 | **Gen-LaneNet: a generalized and scalable approach for 3D lane detection** 1103 | 1104 | - 论文：https://arxiv.org/abs/2003.10656 1105 | - 代码：https://github.com/yuliangguo/Pytorch_Generalized_3D_Lane_Detection 1106 | - 数据集：https://github.com/yuliangguo/3D_Lane_Synthetic_Dataset 1107 | 1108 | 1109 | 1110 | # 轨迹预测 1111 | 1112 | **SimAug: Learning Robust Representations from 3D Simulation for Pedestrian Trajectory Prediction in Unseen Cameras** 1113 | 1114 | - 论文：https://arxiv.org/abs/2004.02022 1115 | - 代码：https://github.com/JunweiLiang/Multiverse 1116 | 1117 | 1118 | 1119 | # 线段检测 1120 | 1121 | **Deep Hough-Transform Line Priors** 1122 | 1123 | - 论文：https://arxiv.org/abs/2007.09493 1124 | 1125 | - 代码：https://github.com/yanconglin/Deep-Hough-Transform-Line-Priors 1126 | 1127 | 1128 | 1129 | # 视线估计 1130 | 1131 | **ETH-XGaze: A Large Scale Dataset for Gaze Estimation under Extreme Head Pose and Gaze Variation** 1132 | 1133 | - 主页：https://ait.ethz.ch/projects/2020/ETH-XGaze 1134 | 1135 | - 论文：https://arxiv.org/abs/2007.15837 1136 | 1137 | 1138 | 1139 | # 眼动追踪 1140 | 1141 | **Towards End-to-end Video-based Eye-Tracking** 1142 | 1143 | - 主页：https://ait.ethz.ch/projects/2020/EVE/ 1144 | - 论文：https://arxiv.org/abs/2007.13120 1145 | 1146 | 1147 | 1148 | # 对抗攻击 1149 | 1150 | **Adversarial Ranking Attack and Defense** 1151 | 1152 | - 论文：https://arxiv.org/abs/2002.11293 1153 | - 代码：https://github.com/cdluminate/advrank 1154 | 1155 | **Square Attack: a query-efficient black-box adversarial attack via random search** 1156 | 1157 | - 论文：https://arxiv.org/abs/1912.00049 1158 | - 代码：https://github.com/max-andr/square-attack 1159 | 1160 | 1161 | 1162 | # 数据集 1163 | 1164 | **Long-term Human Motion Prediction with Scene Context** 1165 | 1166 | - 主页：https://people.eecs.berkeley.edu/~zhecao/hmp/index.html 1167 | - 论文：https://arxiv.org/abs/2007.03672 1168 | 1169 | - 数据集：https://github.com/ZheC/GTA-IM-Dataset 1170 | 1171 | **Object Detection with a Unified Label Space from Multiple Datasets** 1172 | 1173 | - 主页：http://www.nec-labs.com/~mas/UniDet/ 1174 | - 论文：https://arxiv.org/abs/2008.06614 1175 | - 代码：暂无 1176 | - 数据集：http://www.nec-labs.com/~mas/UniDet/resources/UOD_dataset_ECCV20.zip 1177 | 1178 | **Simulating Content Consistent Vehicle Datasets with Attribute Descent** 1179 | 1180 | - 论文：https://arxiv.org/abs/1912.08855 1181 | - 代码：https://github.com/yorkeyao/VehicleX 1182 | - 数据集：https://github.com/yorkeyao/VehicleX 1183 | 1184 | **InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image** 1185 | 1186 | - 主页：https://mks0601.github.io/InterHand2.6M/ 1187 | - 论文：https://arxiv.org/abs/2008.09309 1188 | - 代码：https://github.com/facebookresearch/InterHand2.6M 1189 | 1190 | 1191 | **SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection** 1192 | 1193 | - 主页：https://sites.google.com/view/sne-roadseg 1194 | - 论文：https://arxiv.org/abs/2008.11351 1195 | - 代码：https://github.com/hlwang1124/SNE-RoadSeg 1196 | - 数据集：https://drive.google.com/file/d/1YnkqPmzxtjNfMi2B1gMy7LQa5Gnu-BsH/view 1197 | 1198 | **CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending** 1199 | 1200 | - 论文：https://arxiv.org/abs/2007.12147 1201 | - 数据集：https://github.com/xbjxh/curvelanes 1202 | 1203 | **Detecting natural disasters, damage, and incidents in the wild** 1204 | 1205 | - 主页：http://incidentsdataset.csail.mit.edu/ 1206 | - 论文：https://arxiv.org/abs/2008.09188 1207 | - 数据集：https://github.com/ethanweber/IncidentsDataset 1208 | 1209 | **Simultaneous Detection and Tracking with Motion Modelling for Multiple Object Tracking** 1210 | 1211 | - 论文：https://arxiv.org/abs/2008.08826 1212 | - 代码：https://github.com/shijieS/DMMN 1213 | - 数据集：https://github.com/shijieS/OmniMOTDataset 1214 | 1215 | **3D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single View** 1216 | 1217 | - 主页：https://marcbadger.github.io/avian-mesh/ 1218 | - 论文：https://arxiv.org/abs/2008.06133 1219 | - 代码：https://github.com/marcbadger/avian-mesh 1220 | - 数据集：https://drive.google.com/file/d/1vyXYIJIo9jneIqC7lowB4GVi17rjztjn/view?usp=sharing 1221 | 1222 | **Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards** 1223 | 1224 | - 论文：https://arxiv.org/abs/2008.02693 1225 | 1226 | - 代码： https://github.com/xuewyang/Fashion_Captioning 1227 | - 数据集：https://drive.google.com/drive/folders/1J6SZOt_WFwZToX1Jf7QiXzFVwt23lGwW?usp=sharing 1228 | 1229 | **From Shadow Segmentation to Shadow Removal** 1230 | 1231 | - 论文：http://xxx.itp.ac.cn/abs/2008.00267 1232 | 1233 | - 数据集：https://www3.cs.stonybrook.edu/~cvl/projects/FSS2SR/index.html 1234 | 1235 | **LEMMA: A Multi-view Dataset for Learning Multi-agent Multi-task Activities** 1236 | 1237 | - 主页：https://sites.google.com/view/lemma-activity 1238 | 1239 | - 论文：https://arxiv.org/abs/2007.15781 1240 | 1241 | - 数据集：https://sites.google.com/view/lemma-activity/home/dataset 1242 | - 代码：https://github.com/Buzz-Beater/LEMMA 1243 | 1244 | **Component Divide-and-Conquer for Real-World Image Super-Resolution** 1245 | 1246 | - 论文：https://arxiv.org/abs/2008.01928 1247 | 1248 | - 代码和数据集：https://github.com/xiezw5/Component-Divide-and-Conquer-for-Real-World-Image-Super-Resolution 1249 | 1250 | **Towards End-to-end Video-based Eye-Tracking** 1251 | 1252 | - 主页：https://ait.ethz.ch/projects/2020/EVE/ 1253 | - 论文：https://arxiv.org/abs/2007.13120 1254 | 1255 | **Reconstructing NBA Players** 1256 | 1257 | - 主页：http://grail.cs.washington.edu/projects/nba_players/ 1258 | 1259 | - 论文：https://arxiv.org/abs/2007.13303 1260 | 1261 | **CelebA-Spoof: Large-Scale Face Anti-Spoofing Dataset with Rich Annotations** 1262 | 1263 | - 论文：https://arxiv.org/abs/2007.12342 1264 | 1265 | - 数据集：https://github.com/Davidzhangyuanhan/CelebA-Spoof 1266 | 1267 | **PIoU Loss: Towards Accurate Oriented Object Detection in Complex Environments** 1268 | 1269 | - 论文：https://arxiv.org/abs/2007.09584 1270 | 1271 | - 代码：https://github.com/clobotics/piou 1272 | 1273 | - 数据集：https://github.com/clobotics/piou 1274 | 1275 | **DanbooRegion: An Illustration Region Dataset** 1276 | 1277 | - 主页：https://lllyasviel.github.io/DanbooRegion/ 1278 | 1279 | - 论文：https://lllyasviel.github.io/DanbooRegion/paper/paper.pdf 1280 | 1281 | - 数据集：https://github.com/lllyasviel/DanbooRegion 1282 | 1283 | **Segment as Points for Efficient Online Multi-Object Tracking and Segmentation** 1284 | 1285 | - Oral 1286 | - 论文：https://arxiv.org/abs/2007.01550 1287 | - 代码：https://github.com/detectRecog/PointTrack 1288 | - 数据集：https://github.com/detectRecog/PointTrack 1289 | 1290 | **Gen-LaneNet: a generalized and scalable approach for 3D lane detection** 1291 | 1292 | - 论文：https://arxiv.org/abs/2003.10656 1293 | - 代码：https://github.com/yuliangguo/Pytorch_Generalized_3D_Lane_Detection 1294 | - 数据集：https://github.com/yuliangguo/3D_Lane_Synthetic_Dataset 1295 | 1296 | **TAO: A Large-Scale Benchmark for Tracking Any Object** 1297 | 1298 | - 主页：http://taodataset.org/ 1299 | - 论文：https://arxiv.org/abs/2005.10356 1300 | - 代码：https://github.com/TAO-Dataset/tao 1301 | 1302 | **Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling** 1303 | 1304 | - 主页：[http://structured3d-dataset.org](http://structured3d-dataset.org/) 1305 | - 论文：https://arxiv.org/abs/1908.00222 1306 | - 代码：https://github.com/bertjiazheng/Structured3D 1307 | 1308 | **AiR: Attention with Reasoning Capability** 1309 | 1310 | - 论文：暂无 1311 | 1312 | - 代码：https://github.com/szzexpoi/AiR 1313 | - 数据集：https://github.com/szzexpoi/AiR 1314 | 1315 | 1316 | 1317 | # 其他 1318 | 1319 | **Defocus Blur Detection via Depth Distillation** 1320 | 1321 | - 论文：https://arxiv.org/abs/2007.08113 1322 | - 代码：https://github.com/vinthony/depth-distillation 1323 | 1324 | **Pose Augmentation: Class-agnostic Object Pose Transformation for Object Recognition** 1325 | 1326 | - 论文：https://arxiv.org/abs/2003.08526 1327 | 1328 | - 代码：https://github.com/gyhandy/Pose-Augmentation 1329 | 1330 | **Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems** 1331 | 1332 | - 论文：https://arxiv.org/abs/2008.03043 1333 | - 代码：https://github.com/CalayZhou/MBNet 1334 | - Demo：https://www.bilibili.com/video/BV1Hi4y137aS 1335 | 1336 | **From Shadow Segmentation to Shadow Removal** 1337 | 1338 | 论文：http://xxx.itp.ac.cn/abs/2008.00267 1339 | 1340 | 代码和数据集：https://www3.cs.stonybrook.edu/~cvl/projects/FSS2SR/index.html 1341 | 1342 | **Funnel Activation for Visual Recognition** 1343 | 1344 | - 论文：https://arxiv.org/abs/2007.11824 1345 | 1346 | - 代码：https://github.com/megvii-model/FunnelAct 1347 | 1348 | **Open-Edit: Open-Domain Image Manipulation with Open-Vocabulary Instructions** 1349 | 1350 | - 论文：暂无 1351 | - 代码：https://github.com/xh-liu/Open-Edit 1352 | - Video：https://youtu.be/8E3bwvjCHYE 1353 | 1354 | **Consensus-Aware Visual-Semantic Embedding for Image-Text Matching** 1355 | 1356 | - 论文：https://arxiv.org/abs/2007.08883 1357 | - 代码：https://github.com/BruceW91/CVSE 1358 | 1359 | **Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild** 1360 | 1361 | - 主页：https://jasonyzhang.com/phosa/ 1362 | - 论文下载：https://arxiv.org/abs/2007.15649 1363 | - 代码：https://github.com/jasonyzhang/phosa 1364 | 1365 | **AiR: Attention with Reasoning Capability** 1366 | 1367 | - Oral 1368 | 1369 | - 论文：https://arxiv.org/abs/2007.14419 1370 | 1371 | - 代码：https://github.com/szzexpoi/AiR 1372 | 1373 | **Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets** 1374 | 1375 | - 论文：https://arxiv.org/abs/2007.09654 1376 | - 代码：https://github.com/wutong16/DistributionBalancedLoss 1377 | 1378 | **A Generic Visualization Approach for Convolutional Neural Networks** 1379 | 1380 | - 论文：https://arxiv.org/abs/2007.09748 1381 | 1382 | - 代码：https://github.com/ahmdtaha/constrained_attention_filter 1383 | 1384 | **Deep Plastic Surgery: Robust and Controllable Image Editing with Human-Drawn Sketches** 1385 | 1386 | - 主页：https://williamyang1991.github.io/projects/ECCV2020 1387 | - 论文：https://arxiv.org/abs/2001.02890 1388 | - 代码：https://github.com/TAMU-VITA/DeepPS 1389 | 1390 | **GIQA: Generated Image Quality Assessment** 1391 | 1392 | - 论文：https://arxiv.org/abs/2003.08932 1393 | - 代码：https://github.com/cientgu/GIQA 1394 | 1395 | **Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling** 1396 | 1397 | - 主页：[http://structured3d-dataset.org](http://structured3d-dataset.org/) 1398 | - 论文：https://arxiv.org/abs/1908.00222 1399 | - 代码：https://github.com/bertjiazheng/Structured3D 1400 | 1401 | **AiR: Attention with Reasoning Capability** 1402 | 1403 | - 论文：暂无 1404 | 1405 | - 代码：https://github.com/szzexpoi/AiR 1406 | - 数据集：https://github.com/szzexpoi/AiR 1407 | 1408 | 1409 | 1410 | # 不确定中没中 1411 | 1412 | **Relation Aware Panoptic Segmentation** 1413 | 1414 | - 论文：暂无 1415 | - 代码：https://github.com/RAPNet/RAP 1416 | 1417 | **Spatial-Angular Interaction for Light Field Image Super-Resolution** 1418 | 1419 | - 论文：暂无 1420 | - 代码：https://github.com/YingqianWang/LF-InterNet 1421 | 1422 | **TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval** 1423 | 1424 | - 论文：https://arxiv.org/abs/2001.09099 1425 | - 代码：https://github.com/jayleicn/TVRetrieval 1426 | - 代码：https://github.com/jayleicn/TVCaption 1427 | 1428 | **Self-supervising Fine-grained Region Similarities for IBL** 1429 | 1430 | - 论文：暂无 1431 | - 代码： https://github.com/ID2191/ECCV2020 1432 | 1433 | https://github.com/lelechen63/eccv2020 1434 | 1435 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # ECCV 2024 论文和开源项目合集(Papers with Code) 2 | 3 | ECCV 2024 decisions are now available！ 4 | 5 | 6 | > 注1：欢迎各位大佬提交issue，分享ECCV 2024论文和开源项目！ 7 | > 8 | > 注2：关于往年CV顶会论文以及其他优质CV论文和大盘点，详见： https://github.com/amusi/daily-paper-computer-vision 9 | > 10 | > - [CVPR 2024](https://github.com/amusi/CVPR2024-Papers-with-Code) 11 | > - [ECCV 2022](ECCV2022-Papers-with-Code.md) 12 | > - [ECCV 2020](ECCV2020-Papers-with-Code.md) 13 | 14 | 想看ECCV 2024和最新最全的顶会工作，欢迎扫码加入【CVer学术交流群】，这是最大的计算机视觉AI知识星球！每日更新，第一时间分享最新最前沿的计算机视觉、深度学习、自动驾驶、医疗影像和AIGC等方向的学习资料，学起来！ 15 | 16 | ![](CVer学术交流群.png) 17 | 18 | # 【ECCV 2024 论文开源目录】 19 | 20 | - [3DGS(Gaussian Splatting)](#3DGS) 21 | - [Mamba / SSM)](#Mamba) 22 | - [Avatars](#Avatars) 23 | - [Backbone](#Backbone) 24 | - [CLIP](#CLIP) 25 | - [MAE](#MAE) 26 | - [Embodied AI](#Embodied-AI) 27 | - [GAN](#GAN) 28 | - [GNN](#GNN) 29 | - [多模态大语言模型(MLLM)](#MLLM) 30 | - [大语言模型(LLM)](#LLM) 31 | - [NAS](#NAS) 32 | - [OCR](#OCR) 33 | - [NeRF](#NeRF) 34 | - [DETR](#DETR) 35 | - [Prompt](#Prompt) 36 | - [扩散模型(Diffusion Models)](#Diffusion) 37 | - [ReID(重识别)](#ReID) 38 | - [长尾分布(Long-Tail)](#Long-Tail) 39 | - [Vision Transformer](#Vision-Transformer) 40 | - [视觉和语言(Vision-Language)](#VL) 41 | - [自监督学习(Self-supervised Learning)](#SSL) 42 | - [数据增强(Data Augmentation)](#DA) 43 | - [目标检测(Object Detection)](#Object-Detection) 44 | - [异常检测(Anomaly Detection)](#Anomaly-Detection) 45 | - [目标跟踪(Visual Tracking)](#VT) 46 | - [语义分割(Semantic Segmentation)](#Semantic-Segmentation) 47 | - [实例分割(Instance Segmentation)](#Instance-Segmentation) 48 | - [全景分割(Panoptic Segmentation)](#Panoptic-Segmentation) 49 | - [医学图像(Medical Image)](#MI) 50 | - [医学图像分割(Medical Image Segmentation)](#MIS) 51 | - [视频目标分割(Video Object Segmentation)](#VOS) 52 | - [视频实例分割(Video Instance Segmentation)](#VIS) 53 | - [参考图像分割(Referring Image Segmentation)](#RIS) 54 | - [图像抠图(Image Matting)](#Matting) 55 | - [图像编辑(Image Editing)](#Image-Editing) 56 | - [Low-level Vision](#LLV) 57 | - [超分辨率(Super-Resolution)](#SR) 58 | - [去噪(Denoising)](#Denoising) 59 | - [去模糊(Deblur)](#Deblur) 60 | - [自动驾驶(Autonomous Driving)](#Autonomous-Driving) 61 | - [3D点云(3D Point Cloud)](#3D-Point-Cloud) 62 | - [3D目标检测(3D Object Detection)](#3DOD) 63 | - [3D语义分割(3D Semantic Segmentation)](#3DSS) 64 | - [3D目标跟踪(3D Object Tracking)](#3D-Object-Tracking) 65 | - [3D语义场景补全(3D Semantic Scene Completion)](#3DSSC) 66 | - [3D配准(3D Registration)](#3D-Registration) 67 | - [3D人体姿态估计(3D Human Pose Estimation)](#3D-Human-Pose-Estimation) 68 | - [3D人体Mesh估计(3D Human Mesh Estimation)](#3D-Human-Pose-Estimation) 69 | - [医学图像(Medical Image)](#Medical-Image) 70 | - [图像生成(Image Generation)](#Image-Generation) 71 | - [视频生成(Video Generation)](#Video-Generation) 72 | - [3D生成(3D Generation)](#3D-Generation) 73 | - [视频理解(Video Understanding)](#Video-Understanding) 74 | - [行为识别(Action Recognition)](#Action-Recognition) 75 | - [行为检测(Action Detection)](#Action-Detection) 76 | - [文本检测(Text Detection)](#Text-Detection) 77 | - [知识蒸馏(Knowledge Distillation)](#KD) 78 | - [模型剪枝(Model Pruning)](#Pruning) 79 | - [图像压缩(Image Compression)](#IC) 80 | - [三维重建(3D Reconstruction)](#3D-Reconstruction) 81 | - [深度估计(Depth Estimation)](#Depth-Estimation) 82 | - [轨迹预测(Trajectory Prediction)](#TP) 83 | - [车道线检测(Lane Detection)](#Lane-Detection) 84 | - [图像描述(Image Captioning)](#Image-Captioning) 85 | - [视觉问答(Visual Question Answering)](#VQA) 86 | - [手语识别(Sign Language Recognition)](#SLR) 87 | - [视频预测(Video Prediction)](#Video-Prediction) 88 | - [新视点合成(Novel View Synthesis)](#NVS) 89 | - [Zero-Shot Learning(零样本学习)](#ZSL) 90 | - [立体匹配(Stereo Matching)](#Stereo-Matching) 91 | - [特征匹配(Feature Matching)](#Feature-Matching) 92 | - [场景图生成(Scene Graph Generation)](#SGG) 93 | - [计数(Counting)](#Counting) 94 | - [隐式神经表示(Implicit Neural Representations)](#INR) 95 | - [图像质量评价(Image Quality Assessment)](#IQA) 96 | - [视频质量评价(Video Quality Assessment)](#Video-Quality-Assessment) 97 | - [数据集(Datasets)](#Datasets) 98 | - [新任务(New Tasks)](#New-Tasks) 99 | - [其他(Others)](#Others) 100 | 101 | 102 | 103 | # 3DGS(Gaussian Splatting) 104 | 105 | **MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images** 106 | 107 | - Project: https://donydchen.github.io/mvsplat 108 | - Paper: https://arxiv.org/abs/2403.14627 109 | - Code：https://github.com/donydchen/mvsplat 110 | 111 | **CityGaussian: Real-time High-quality Large-Scale Scene Rendering with Gaussians** 112 | 113 | - Paper: https://arxiv.org/abs/2404.01133 114 | - Code: https://github.com/DekuLiuTesla/CityGaussian 115 | 116 | **FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting** 117 | 118 | - Project: https://zehaozhu.github.io/FSGS/ 119 | - Paper: https://arxiv.org/abs/2312.00451 120 | - Code: https://github.com/VITA-Group/FSGS 121 | 122 | 123 | 124 | 125 | 126 | # Mamba / SSM 127 | 128 | **VideoMamba: State Space Model for Efficient Video Understanding** 129 | 130 | - Paper: https://arxiv.org/abs/2403.06977 131 | - Code: https://github.com/OpenGVLab/VideoMamba 132 | 133 | **ZIGMA: A DiT-style Zigzag Mamba Diffusion Model** 134 | 135 | - Paper: https://arxiv.org/abs/2403.13802 136 | - Code: https://taohu.me/zigma/ 137 | 138 | 139 | 140 | # Avatars 141 | 142 | 143 | 144 | 145 | 146 | 147 | 148 | # Backbone 149 | 150 | 151 | 152 | 153 | 154 | # CLIP 155 | 156 | 157 | 158 | 159 | 160 | 161 | 162 | # MAE 163 | 164 | 165 | 166 | # Embodied AI 167 | 168 | 169 | 170 | 171 | 172 | # GAN 173 | 174 | 175 | 176 | # OCR 177 | 178 | **Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors** 179 | 180 | - Paper: https://arxiv.org/pdf/2312.05286 181 | 182 | - Code: https://github.com/SJTU-DeepVisionLab/FreeReal 183 | 184 | **PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer** 185 | 186 | - Paper: https://arxiv.org/abs/2407.07764 187 | - Code: https://github.com/SJTU-DeepVisionLab/PosFormer 188 | 189 | 190 | 191 | # Occupancy 192 | 193 | **Fully Sparse 3D Occupancy Prediction** 194 | 195 | - Paper: https://arxiv.org/abs/2312.17118 196 | - Code: https://github.com/MCG-NJU/SparseOcc 197 | 198 | 199 | 200 | 201 | 202 | # NeRF 203 | 204 | **NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields** 205 | 206 | - Project: https://nerf-mae.github.io/ 207 | - Paper: https://arxiv.org/pdf/2404.01300 208 | - Code: https://github.com/zubair-irshad/NeRF-MAE 209 | 210 | 211 | 212 | # DETR 213 | 214 | 215 | 216 | 217 | 218 | # Prompt 219 | 220 | 221 | 222 | # 多模态大语言模型(MLLM) 223 | 224 | **SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant** 225 | 226 | - Paper: https://arxiv.org/abs/2403.11299 227 | - Code: https://github.com/heliossun/SQ-LLaVA 228 | 229 | **ControlCap: Controllable Region-level Captioning** 230 | 231 | - Paper: https://arxiv.org/abs/2401.17910 232 | - Code: https://github.com/callsys/ControlCap 233 | 234 | 235 | 236 | # 大语言模型(LLM) 237 | 238 | 239 | 240 | 241 | 242 | # NAS 243 | 244 | 245 | 246 | # ReID(重识别) 247 | 248 | 249 | 250 | 251 | 252 | # 扩散模型(Diffusion Models) 253 | 254 | **ZIGMA: A DiT-style Zigzag Mamba Diffusion Model** 255 | 256 | - Paper: https://arxiv.org/abs/2403.13802 257 | - Code: https://taohu.me/zigma/ 258 | 259 | **Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation** 260 | 261 | - Paper: https://arxiv.org/abs/2403.16394 262 | - Code: https://github.com/zdxdsw/skewed_relations_T2I 263 | 264 | **The Lottery Ticket Hypothesis in Denoising: Towards Semantic-Driven Initialization** 265 | 266 | - Project: https://ut-mao.github.io/noise.github.io/ 267 | - Paper: https://arxiv.org/abs/2312.08872 268 | - Code: https://github.com/UT-Mao/Initial-Noise-Construction 269 | 270 | 271 | 272 | # Vision Transformer 273 | 274 | **GiT: Towards Generalist Vision Transformer through Universal Language Interface** 275 | 276 | - Paper: https://arxiv.org/abs/2403.09394 277 | - Code: https://github.com/Haiyang-W/GiT 278 | 279 | 280 | 281 | # 视觉和语言(Vision-Language) 282 | 283 | **GalLoP: Learning Global and Local Prompts for Vision-Language Models** 284 | 285 | - Paper：https://arxiv.org/abs/2407.01400 286 | 287 | 288 | 289 | # 目标检测(Object Detection) 290 | 291 | **Relation DETR: Exploring Explicit Position Relation Prior for Object Detection** 292 | 293 | - Paper: https://arxiv.org/abs/2407.11699v1 294 | - Code: https://github.com/xiuqhou/Relation-DETR 295 | - Dataset: https://huggingface.co/datasets/xiuqhou/SA-Det-100k 296 | 297 | **Cross-Domain Few-Shot Object Detection via Enhanced Open-Set Object Detector** 298 | 299 | - Project: http://yuqianfu.com/CDFSOD-benchmark/ 300 | - Paper: https://arxiv.org/pdf/2402.03094 301 | - Code: https://github.com/lovelyqian/CDFSOD-benchmark 302 | 303 | 304 | 305 | # 异常检测(Anomaly Detection) 306 | 307 | 308 | 309 | 310 | 311 | # 目标跟踪(Object Tracking) 312 | 313 | 314 | 315 | 316 | 317 | 318 | 319 | # 语义分割(Semantic Segmentation) 320 | 321 | **Context-Guided Spatial Feature Reconstruction for Efficient Semantic Segmentation** 322 | 323 | - Paper: https://arxiv.org/abs/2405.06228 324 | 325 | - Code: https://github.com/nizhenliang/CGRSeg 326 | 327 | 328 | 329 | # 医学图像(Medical Image) 330 | 331 | **Brain-ID: Learning Contrast-agnostic Anatomical Representations for Brain Imaging** 332 | 333 | - Paper: https://arxiv.org/abs/2311.16914 334 | - Code: https://github.com/peirong26/Brain-ID 335 | 336 | **FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classification** 337 | 338 | - Project: https://ophai.hms.harvard.edu/datasets/harvard-fairdomain20k 339 | - Paper : https://arxiv.org/abs/2407.08813 340 | - Dataset: https://drive.google.com/drive/u/1/folders/1huH93JVeXMj9rK6p1OZRub868vv0UK0O 341 | - Code: https://github.com/Harvard-Ophthalmology-AI-Lab/FairDomain 342 | 343 | 344 | 345 | # 医学图像分割(Medical Image Segmentation) 346 | 347 | **ScribblePrompt: Fast and Flexible Interactive Segmentation for Any Biomedical Image** 348 | 349 | - Project: https://scribbleprompt.csail.mit.edu/ 350 | - Paper: https://arxiv.org/abs/2312.07381 351 | - Code: https://github.com/halleewong/ScribblePrompt 352 | 353 | **AnatoMask: Enhancing Medical Image Segmentation with Reconstruction-guided Self-masking** 354 | 355 | - Paper: https://arxiv.org/abs/2407.06468 356 | - Code: https://github.com/ricklisz/AnatoMask 357 | 358 | **Representing Topological Self-Similarity Using Fractal Feature Maps for Accurate Segmentation of Tubular Structures** 359 | 360 | - Paper: https://arxiv.org/abs/2407.14754 361 | - Code: https://github.com/cbmi-group/FFM-Multi-Decoder-Network 362 | 363 | 364 | 365 | # 视频目标分割(Video Object Segmentation) 366 | 367 | **DVIS-DAQ: Improving Video Segmentation via Dynamic Anchor Queries** 368 | 369 | - Project: https://zhang-tao-whu.github.io/projects/DVIS_DAQ/ 370 | - Paper: https://arxiv.org/abs/2404.00086 371 | - Code: https://github.com/zhang-tao-whu/DVIS_Plus 372 | 373 | 374 | 375 | # 自动驾驶(Autonomous Driving) 376 | 377 | **Fully Sparse 3D Occupancy Prediction** 378 | 379 | - Paper: https://arxiv.org/abs/2312.17118 380 | - Code: https://github.com/MCG-NJU/SparseOcc 381 | 382 | **milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing** 383 | 384 | - Paper: https://arxiv.org/abs/2306.17010 385 | - Code: https://github.com/Toytiny/milliFlow/ 386 | 387 | **4D Contrastive Superflows are Dense 3D Representation Learners** 388 | 389 | - Paper : https://arxiv.org/abs/2407.06190 390 | - Code: https://github.com/Xiangxu-0103/SuperFlow 391 | 392 | 393 | 394 | # 3D点云(3D-Point-Cloud) 395 | 396 | 397 | 398 | 399 | 400 | # 3D目标检测(3D Object Detection) 401 | 402 | **3D Small Object Detection with Dynamic Spatial Pruning** 403 | 404 | - Project: https://xuxw98.github.io/DSPDet3D/ 405 | - Paper: https://arxiv.org/abs/2305.03716 406 | - Code: https://github.com/xuxw98/DSPDet3D 407 | 408 | **Ray Denoising: Depth-aware Hard Negative Sampling for Multi-view 3D Object Detection** 409 | 410 | - Paper: https://arxiv.org/abs/2402.03634 411 | - Code: https://github.com/LiewFeng/RayDN 412 | 413 | 414 | 415 | # 3D语义分割(3D Semantic Segmentation) 416 | 417 | 418 | 419 | # 图像编辑(Image Editing) 420 | 421 | 422 | 423 | 424 | 425 | 426 | 427 | # 图像补全/图像修复(Image Inpainting) 428 | 429 | **BrushNet: A Plug-and-Play Image Inpainting Model with Decomposed Dual-Branch Diffusion** 430 | 431 | - Project https://tencentarc.github.io/BrushNet/ 432 | - Paper: https://arxiv.org/abs/2403.06976 433 | - Code: https://github.com/TencentARC/BrushNet 434 | 435 | 436 | 437 | # 视频编辑(Video Editing) 438 | 439 | 440 | 441 | 442 | 443 | # Low-level Vision 444 | 445 | **Restoring Images in Adverse Weather Conditions via Histogram Transformer** 446 | 447 | - Paper: https://arxiv.org/abs/2407.10172 448 | - Code: https://github.com/sunshangquan/Histoformer 449 | 450 | **OneRestore: A Universal Restoration Framework for Composite Degradation** 451 | 452 | - Project https://gy65896.github.io/projects/ECCV2024_OneRestore 453 | - Paper: https://arxiv.org/abs/2407.04621 454 | - Code: https://github.com/gy65896/OneRestore 455 | 456 | # 超分辨率(Super-Resolution) 457 | 458 | 459 | 460 | 461 | 462 | # 去噪(Denoising) 463 | 464 | ## 图像去噪(Image Denoising) 465 | 466 | 467 | 468 | # 3D人体姿态估计(3D Human Pose Estimation) 469 | 470 | 471 | 472 | 473 | 474 | # 图像生成(Image Generation) 475 | 476 | **Object-Conditioned Energy-Based Attention Map Alignment in Text-to-Image Diffusion Models** 477 | 478 | - Paper: https://arxiv.org/abs/2404.07389 479 | - Code: https://github.com/YasminZhang/EBAMA 480 | 481 | **Every Pixel Has its Moments: Ultra-High-Resolution Unpaired Image-to-Image Translation via Dense Normalization** 482 | 483 | - Project: https://kaminyou.com/Dense-Normalization/ 484 | - Paper: https://arxiv.org/abs/2407.04245 485 | - Code: https://github.com/Kaminyou/Dense-Normalization 486 | 487 | **ZIGMA: A DiT-style Zigzag Mamba Diffusion Model** 488 | 489 | - Paper: https://arxiv.org/abs/2403.13802 490 | - Code: https://taohu.me/zigma/ 491 | 492 | **Skews in the Phenomenon Space Hinder Generalization in Text-to-Image Generation** 493 | 494 | - Paper: https://arxiv.org/abs/2403.16394 495 | - Code: https://github.com/zdxdsw/skewed_relations_T2I 496 | 497 | 498 | 499 | # 视频生成(Video Generation) 500 | 501 | **VideoStudio: Generating Consistent-Content and Multi-Scene Videos** 502 | 503 | - Project: https://vidstudio.github.io/ 504 | - Code: https://github.com/FuchenUSTC/VideoStudio 505 | 506 | 507 | 508 | 509 | 510 | # 3D生成 511 | 512 | 513 | 514 | 515 | 516 | # 视频理解(Video Understanding) 517 | 518 | **VideoMamba: State Space Model for Efficient Video Understanding** 519 | 520 | - Paper: https://arxiv.org/abs/2403.06977 521 | - Code: https://github.com/OpenGVLab/VideoMamba 522 | 523 | **C2C: Component-to-Composition Learning for Zero-Shot Compositional Action Recognition** 524 | 525 | - Paper: https://arxiv.org/abs/2407.06113 526 | - Code: https://github.com/RongchangLi/ZSCAR_C2C 527 | 528 | 529 | 530 | # 行为识别(Action Recognition) 531 | 532 | **SA-DVAE: Improving Zero-Shot Skeleton-Based Action Recognition by Disentangled Variational Autoencoders** 533 | 534 | - Paper: https://arxiv.org/abs/2407.13460 535 | - Code: https://github.com/pha123661/SA-DVAE 536 | 537 | 538 | 539 | # 知识蒸馏(Knowledge Distillation) 540 | 541 | 542 | 543 | # 图像压缩(Image Compression) 544 | 545 | **Image Compression for Machine and Human Vision With Spatial-Frequency Adaptation** 546 | 547 | - Code: https://github.com/qingshi9974/ECCV2024-AdpatICMH 548 | - Paper: http://arxiv.org/abs/2407.09853 549 | 550 | 551 | 552 | # 立体匹配(Stereo Matching) 553 | 554 | 555 | 556 | 557 | 558 | # 场景图生成(Scene Graph Generation) 559 | 560 | 561 | 562 | 563 | 564 | # 计数(Counting) 565 | 566 | **Zero-shot Object Counting with Good Exemplars** 567 | 568 | - Paper: https://arxiv.org/abs/2407.04948 569 | - Code: https://github.com/HopooLinZ/VA-Count 570 | 571 | 572 | 573 | 574 | 575 | # 视频质量评价(Video Quality Assessment) 576 | 577 | 578 | 579 | # 数据集(Datasets) 580 | 581 | 582 | 583 | # 其他(Others) 584 | 585 | **Multi-branch Collaborative Learning Network for 3D Visual Grounding** 586 | 587 | - Paper: https://arxiv.org/abs/2407.05363v2 588 | - Code: https://github.com/qzp2018/MCLN 589 | 590 | **PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers** 591 | 592 | - Code: https://github.com/ananthu-aniraj/pdiscoformer 593 | - Paper: https://arxiv.org/abs/2407.04538 594 | 595 | **SPVLoc: Semantic Panoramic Viewport Matching for 6D Camera Localization in Unseen Environments** 596 | 597 | - Project: https://fraunhoferhhi.github.io/spvloc/ 598 | - Paper: https://arxiv.org/abs/2404.10527 599 | - Code: https://github.com/fraunhoferhhi/spvloc 600 | 601 | **REFRAME: Reflective Surface Real-Time Rendering for Mobile Devices** 602 | 603 | - Project: https://xdimlab.github.io/REFRAME/ 604 | - Paper: https://arxiv.org/abs/2403.16481 605 | - Code: https://github.com/MARVELOUSJI/REFRAME --------------------------------------------------------------------------------