└── readme.md /readme.md: -------------------------------------------------------------------------------- 1 | 2 | # awesome-visual-place-recognition 3 | # 榜单 4 | https://paperswithcode.com/task/visual-place-recognition 5 | ![image](https://github.com/slz929/awesome-visual-place-recognition/assets/17669514/7f5948af-1d63-4e77-b61a-c0b4a74e1f2a) 6 | 7 | 8 | # 测评工具 9 | 10 | https://github.com/gmberton/VPR-methods-evaluation 11 | 12 | # 数据集 13 | https://github.com/gmberton/VPR-datasets-downloader 14 | 15 | https://github.com/amaralibey/gsv-cities 16 | 17 | https://github.com/mapillary/mapillary_sls 18 | 19 | ALTO: A Large-Scale Dataset for UAV Visual Place Recognition and Localization 20 | https://github.com/MetaSLAM/ALT 21 | 22 | 23 | VPR-Bench： an open-source Visual Place Recognition evaluation framework with quantifiable viewpoint and illumination invariance. 24 | https://github.com/MubarizZaffar/VPR-Bench 25 | 26 | 27 | Deep Visual Geo-localization Benchmark 28 | https://github.com/gmberton/deep-visual-geo-localization-benchmark 29 | 30 | AmsterTime: A Visual Place Recognition Benchmark Dataset for Severe Domain Shift 31 | https://github.com/seyrankhademi/AmsterTime 32 | 33 | 34 | # 综述 35 | General Place Recognition Survey: Towards the Real-world Autonomy Age 36 | https://github.com/MetaSLAM/GPRS 37 | 38 | 39 | # 大模型方法 40 | [cvpr2024][sota] BoQ: A Place is Worth a Bag of Learnable Queries [https://github.com/amaralibey/bag-of-queries] 41 | 42 | [sota]EffoVPR: Effective Foundation Model Utilization for Visual Place Recognition 43 | 44 | 【CVPR 2024】CricaVPR: Cross-image Correlation-aware Representation Learning for Visual Place Recognition 45 | https://github.com/Lu-Feng/CricaVPR 46 | 47 | 【ICLR 2024】[SelaVPR] Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition 48 | https://github.com/Lu-Feng/SelaVPR 49 | 50 | ProGEO: Generating Prompts through Image-Text Contrastive Learning for Visual Geo-localization [https://github.com/chain-mao/progeo] 51 | 52 | 【SOTA】DINO-Mix: Enhancing Visual Place Recognition with Foundational Vision Model and Feature Mixing 53 | https://github.com/GaoShuang98/DINO-Mix 54 | 55 | [sota] Optimal Transport Aggregation for Visual Place Recognition 56 | https://github.com/serizba/salad 57 | 58 | AnyLoc: Towards Universal Visual Place Recognition 59 | [https://github.com/AnyLoc/AnyLoc] 60 | 61 | # 传统方法 62 | 63 | 【2013cvpr】all about vlad 64 | 65 | Long-Term Visual Place Recognition Benchmark with View Direction and Data Anonymization Influences 66 | https://github.com/ai4ce/NYU-VPR 67 | 68 | # cnn-based 69 | netvlad 70 | 71 | GEM 72 | Fine-tuning CNN Image Retrieval with No Human Annotation 73 | 74 | ap loss 75 | ap-gem(DIR):Learning with Average Precision: Training Image Retrieval with a Listwise Loss 76 | https://github.com/naver/deep-image-retrieval 77 | 78 | MultiRes-NetVLAD: Augmenting Place Recognition Training with Low-Resolution Imagery 79 | https://github.com/Ahmedest61/MultiRes-NetVLAD 80 | 81 | Correlation Verification for Image Retrieval 82 | https://github.com/sungonce/CVNet 83 | 84 | # transformer based 85 | 86 | LEARNING SUPER-FEATURES FOR IMAGE RETRIEVAL 87 | https://github.com/Vincentqyw/fire 88 | 89 | TransVPR: Transformer-based place recognition with multi-level attention aggregation 90 | https://github.com/RuotongWANG/TransVPR-model-implementation 91 | 92 | 93 | TransVLAD: Multi-Scale Attention-Based Global Descriptors for Visual Geo-Localization 94 | https://github.com/wacv-23/TVLAD 95 | 96 | 【sota wacv2023】MixVPR: Feature Mixing for Visual Place Recognition 97 | https://github.com/amaralibey/MixVPR 98 | 99 | 100 | # 结合语义 101 | 【ICIAP 2021】Learning Semantics for Visual Place Recognition through Multi-Scale Attention 102 | https://github.com/valeriopaolicelli/SegVPR 103 | 104 | StructVPR: Distill Structural Knowledge with Weighting Samples for Visual Place Recognition 105 | 106 | 107 | A Novel Image Descriptor with Aggregated Semantic Skeleton Representation for Long-term Visual Place Recognition 108 | 109 | 110 | # 轻量化 111 | 112 | MobileNetVLAD 113 | [CoRL 2018]Leveraging Deep Visual Descriptors for Hierarchical Efficient Localization 114 | https://github.com/ethz-asl/hierarchical_loc 115 | 116 | hfnet 117 | From Coarse to Fine: Robust Hierarchical Localization at Large Scale 118 | https://github.com/ethz-asl/hfnet 119 | 120 | 【2022 iros】LSDNet: A Lightweight Self-Attentional Distillation Network for Visual Place Recognition 121 | 122 | 123 | # 局部特征结合 124 | 125 | delf：Large-Scale Image Retrieval with Attentive Deep Local Features 126 | https://github.com/nashory/DeLF-pytorch 127 | 128 | DELG 129 | Unifying Deep Local and Global Features for Image Search 130 | https://github.com/feymanpriv/DELG 131 | https://github.com/ditwoo/pytorch-delg-example 132 | 133 | DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features (ICCV 2021) 134 | https://github.com/dongkyuk/DOLG-pytorch 135 | https://github.com/feymanpriv/DOLG 136 | https://github.com/feymanpriv/DOLG-paddle 137 | https://github.com/tanzeyy/DOLG-instance-retrieval 138 | 139 | DALG: Deep Attentive Local and Global Modeling for Image Retrieval 140 | 141 | 142 | # loss与采样 143 | 144 | Global Proxy-based Hard Mining for Visual Place Recognition（BMVC22） 145 | https://github.com/amaralibey/GPM 146 | 147 | 148 | # 排序 149 | [CVPR IMW 2023]Are Local Features All You Need for Cross-Domain Visual Place Recognition? 150 | https://github.com/gbarbarani/re-ranking-for-VPR 151 | 152 | Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognition 153 | https://github.com/QVPR/Patch-NetVLAD 154 | 155 | R2Former: Unified retrieval and reranking Transformer for Place Recognition. 156 | https://github.com/Jeff-Zilence/R2Former 157 | 158 | 【wacv2023】ETR: An Efficient Transformer for Re-Ranking in Visual Place Recognition 159 | https://github.com/HeartbreakSurvivor/ETR 160 | 161 | 162 | Instance-level Image Retrieval using Reranking Transformers 163 | https://github.com/uvavision/RerankingTransformer 164 | 165 | 166 | iccv2023 Global Features are All You Need for Image Retrieval and Reranking 167 | https://github.com/ShihaoShao-GH/SuperGlobal 168 | 169 | 170 | # 标注方式 171 | 172 | CamNet: Coarse-to-Fine Retrieval for Camera Re-Localization, ICCV 2019 173 | https://github.com/dingmyu/CamNet 174 | 175 | 【sota cvpr2023 GCL】Data-efficient Large Scale Place Recognition with Graded Similarity Supervision 176 | https://github.com/marialeyvallina/generalized_contrastive_loss 177 | 178 | 【CVPR 2022 】Rethinking Visual Geo-localization for Large-Scale Applications 179 | https://github.com/gmberton/CosPlace 180 | 181 | 182 | 183 | # 序列匹配 184 | 185 | Fast and Memory Efficient Graph Optimization via ICM for Visual Place Recognition 186 | 187 | 188 | 189 | 【2012icra】SeqSLAM: Visual Route-Based Navigation for Sunny Summer Days and Stormy Winter Nights 190 | 191 | https://github.com/tmadl/pySeqSLAM 192 | https://github.com/MetaSLAM/MRLoc 193 | https://github.com/subokita/OpenSeqSLAM 194 | https://github.com/siam1251/Fast-SeqSLAM 195 | 196 | (2019 seqslam加速)MRS-VPR: a multi-resolution sampling based global visual place recognition method 197 | 198 | 199 | SeqNet: Learning Descriptors for Sequence-based Hierarchical Place Recognition 200 | SeqNetVLAD vs PointNetVLAD: Image Sequence vs 3D Point Clouds for Day-Night Place Recognition 201 | https://github.com/oravus/seqNet 202 | 203 | 204 | 【CoRL 2021 Oral】SeqMatchNet: Contrastive Learning with Sequence Matching for Place Recognition and Relocalization 205 | https://github.com/oravus/SeqMatchNet 206 | 207 | 208 | SeqVLAD 209 | Learning Sequential Descriptors for Sequence-based Visual Place Recognition 210 | https://github.com/vandal-vpr/vg-transformers 211 | 212 | 213 | Lazy data association for image sequence matching under substantial appearance changes. 214 | https://github.com/PRBonn/online_place_recognition 215 | 216 | ICRA 2020 paper: Fast, Compact and Highly Scalable Visual Place Recognition through Sequence-based Matching of Overloaded Representations 217 | https://github.com/youjiangxu/seqvlad-pytorch 218 | 219 | Tracking‐DOSeqSLAM: A dynamic sequence‐based visual place recognition paradig 220 | https://github.com/ktsintotas/tracking-DOSeqSLAM 221 | 222 | 223 | DeepSeqSLAM: A Trainable CNN+RNN for Joint Global Description and Sequence-based Place Recognition 224 | https://github.com/mchancan/deepseqslam 225 | 226 | 【2018TIP】Sequential Video VLAD: Training the Aggregation Locally and Temporally 227 | https://github.com/oravus/CoarseHash 228 | 229 | Using Image Sequences for Long-Term Visual Localization 230 | https://github.com/rulllars/SequentialVisualLocalization 231 | 232 | 233 | SeqOT: A Spatial-Temporal Transformer Network for Place Recognition Using Sequential LiDAR Data. 234 | https://github.com/BIT-MJY/SeqOT 235 | 236 | 237 | STA-VPR: Spatio-temporal Alignment for Visual Place Recognition 238 | https://github.com/Lu-Feng/STA-VPR 239 | 240 | 241 | iccv23 Learning Sequence Descriptor based on Spatio-Temporal Attention for Visual Place Recognition 242 | 243 | # 视角鲁棒性 244 | EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition 245 | https: //github.com/gmberton/EigenPlaces 246 | while results with any other baseline can be computed with the codebase at https://github.com/gmberton/auto_VPR 247 | 248 | 249 | # 全景 250 | PanoVPR: Towards Unified Perspective-to-Equirectangular Visual Place Recognition via Sliding Windows across the Panoramic View 251 | https://github.com/zafirshi/PanoVPR 252 | 253 | # 交叉视角 254 | TransGeo: Transformer Is All You Need for Cross-view Image Geo-localization 255 | https://github.com/Jeff-Zilence/TransGeo2022 256 | 257 | 258 | CVLNet: Cross-View Semantic Correspondence Learning for Video-based Camera Localization 259 | 260 | 261 | 262 | # 域自适应 263 | AdAGeo: Adaptive-Attentive Geolocalization from few queries: a hybrid approach 264 | https://github.com/valeriopaolicelli/adageo-WACV2021 265 | 266 | # city-wide VPR 267 | Divide&Classify: Fine-Grained Classification for City-Wide Visual Place Recognition 268 | https://github.com/ga1i13o/Divide-and-Classify 269 | 270 | # world-wide VPR 271 | Where in the World is this Image? Transformer-based Geo-localization in the Wild 272 | https://github.com/ShramanPramanick/Transformer_Based_Geo-localization 273 | 274 | 275 | # 脉冲神经网络 276 | VPRTempo: A Fast Temporally Encoded Spiking Neural Network for Visual Place Recognition 277 | --------------------------------------------------------------------------------