├── README.md └── imgs ├── Contant-Aware-DeepH-Data.jpg ├── DIR-D2022.png ├── GES50_2022.jpg ├── LPC2021.jpg ├── NISwGSP.jpg ├── REW.png ├── SPHP.jpg ├── SPW2020.jpg ├── SVA2011.png ├── UDIS-D.png ├── VPG2020.png ├── WSSN2022.png ├── apap.jpg ├── bras.png ├── colorconsistency2019.png ├── hmg-dynamics-2020.png ├── multi_regis.png ├── object_center.png ├── openpano.jpg ├── parallax-tolerant_stitch.jpg ├── parallax-tolerant_stitch2.jpg ├── seagull.jpg └── stereostitch_dataset.png /README.md: -------------------------------------------------------------------------------- 1 | # Image Stitching by Line-guided Local Warping with Global Similarity Constraint (PR2018) 2 | 3 |

4 | 5 | 6 | 7 |

8 | 9 | A collection of image stitching datasets used for image stitching by line-guided local warping with global similarity constraint, PR, 2018. 10 | 11 | Recent image stitching work can be found in: [awesome-computational-photography](https://github.com/visionxiang/awesome-computational-photography). 12 | 13 | If you find this work useful, please cite our paper: 14 | 15 | ``` 16 | @article{xiang2018image, 17 | title={Image Stitching by Line-guided Local Warping with Global Similarity Constraint}, 18 | author={Xiang, Tian-Zhu and Xia, Gui-Song and Bai, Xiang and Zhang, Liangpei}, 19 | journal={Pattern Recognition}, 20 | volume={83}, 21 | pages={481--497}, 22 | year={2018}, 23 | publisher={Elsevier} 24 | } 25 | ``` 26 | 27 | 28 | ## Content 29 | - [Traditional Image Stitching](#Traditional-Image-Stitching) 30 | - [SVA Dataset (2011)](#SVA) 31 | - [APAP Dataset (2013)](#APAP) 32 | - [Parallax-tolerant Stitching Dataset (2014)](#Parallaxtolerant) 33 | - [SPHP Dataset (2014)](#SPHP) 34 | - [Stereostitch Dataset (2015)](#Stereostitch) 35 | - [NISwGSP Dataset (2016)](#NISwGSP) 36 | - [SEAGULL Dataset (2016)](#SEAGULL) 37 | - [REW Dataset (2018)](#REW) 38 | - [Dataset - Multiple Registrations (2018)](#multiregis) 39 | - [Object-Centered Stitching Dataset (2018)](#objcenter) 40 | - [BRAS Dataset (2019)](#BRAS) 41 | - [SPW Dataset (2020)](#SPW) 42 | - [VPG Dataset (2020)](#VPG) 43 | - [LPC Dataset (2021)](#LPC) 44 | - [GES-50 (2022)](#GES50) 45 | - [Color Consistency Dataset (2019)](#colorconsistency) 46 | - [OpenPano Dataset (2016)](#openpano) 47 | - [Aerial Image Stitching Dataset](#AIS) 48 | - [Deep Learning Image Stitching](#Deep-Learning-Image-Stitching) 49 | - [Hmg-dynamics (2020)](#hmgdynamics) 50 | - [Content-Aware-DeepH-Data (2020)](#CADH) 51 | - [UDIS-D (2021)](#UDISD) 52 | - [DIR-D (2022)](#DIRD) 53 | - [WSSN Dataset (2022)](#WSSN) 54 | 55 | 56 | 57 | 58 | ## Traditional Image Stitching 59 | 60 | ### SVA Dataset (2011) 61 | 62 | 63 |   image 64 | - Paper: [Smoothly varying affine stitching](https://ieeexplore.ieee.org/abstract/document/5995314), CVPR2011 65 | - Project: No 66 | - Download: [dataset](https://drive.google.com/drive/folders/1FciKXGD0p_5Ly8_gQDkM2WUdSNRvxBuC?usp=sharing) 67 | - Details: The dataset contains 5 sets of images for image stitching, ranging from 2 to 3 images. 68 | 69 | 70 | 71 | ### APAP Dataset (2013) 72 | 73 | 74 |   image 75 | - Paper: As-Projective-As-Possible Image Stitching with Moving DLT, [CVPR2013](https://cs.adelaide.edu.au/~tjchin/apap/files/mdlt.pdf), [TPAMI2014](https://cs.adelaide.edu.au/~tjchin/apap/files/tpami_mdlt_lowres.pdf) 76 | - Project: [Official](https://cs.adelaide.edu.au/~tjchin/apap/), [Python Code](https://github.com/EadCat/APAP-Image-Stitching), [C++](https://github.com/egoist-sx/AsProjectiveAsPossible) 77 | - Download: [dataset](https://cs.adelaide.edu.au/~tjchin/apap/#Datasets) 78 | - Details: 8 sets of images, including railtracks, temple, carpark, apartment, chess/girl, construction site, and garden. 79 | - Reference:
80 | [18] Smoothly varying affine stitching, CVPR2011.
81 | [22] Constructing image panoramas using dual-homography warping, CVPR2011. 82 | 83 | 84 | 85 | 86 | ### Parallax-tolerant Stitching Dataset (2014) 87 | 88 | 89 |   image 90 | - Paper: [Parallax-tolerant Image Stitching](https://pages.cs.wisc.edu/~fliu/papers/cvpr2014-stitching.pdf), CVPR2014 91 | - Project: https://pages.cs.wisc.edu/~fliu/project/stitch/index.htm 92 | - Download: [Zip](https://pages.cs.wisc.edu/~fliu/project/stitch/dataset.zip), [Imgs](https://web.cecs.pdx.edu/~fliu/project/stitch/dataset.html) 93 | - Details: The dataset contains 36 sets of images for two-view image stitching. 94 | 95 | 96 | ### SPHP Dataset (2014) 97 | 98 | 99 |   image 100 | - Paper: [Shape-Preserving Half-Projective Warps for Image Stitching](https://openaccess.thecvf.com/content_cvpr_2014/papers/Chang_Shape-Preserving_Half-Projective_Warps_2014_CVPR_paper.pdf), CVPR2014 101 | - Related Paper: [Spatially-Varying Image Warps for Scene Alignment](https://www.csie.ntu.edu.tw/~cyy/publications/papers/Chang2014SVI.pdf), ICPR2014 102 | - Project: [Code] 103 | - Download: [dataset](https://drive.google.com/drive/folders/1RRIXj4gn_qN93p58Sh1lUOxh_8L1RRr9?usp=sharing) 104 | - Details: Add another 7 sets of images for image stitching based on the APAP dataset. 105 | 106 | 107 | ### Stereostitch Dataset (2015) 108 | 109 | 110 |   image 111 | - Paper: [Casual Stereoscopic Panorama Stitching](https://pages.cs.wisc.edu/~fliu/papers/cvpr2015-panorama.pdf), CVPR2015 112 | - Project: https://pages.cs.wisc.edu/~fliu/project/stereostitch/ 113 | - Download: [dataset](https://pages.cs.wisc.edu/~fliu/project/stereostitch/dataset.zip) 114 | - Details: The dataset contains 22 sets of images (incl. one group of images for 360 stitching), taken by stereo cameras Fujifilm FinePix 3D W3 and Panasonic HDC-Z10000. Each set of images includes both the left images and right images exhibiting large parallax. 115 | 116 | 117 | ### NISwGSP Dataset (2016) 118 | 119 | 120 |   image 121 | - Paper: [Natural Image Stitching with the Global Similarity Prior](https://link.springer.com/chapter/10.1007/978-3-319-46454-1_12), ECCV2016 122 | - Project: https://github.com/nothinglo/NISwGSP 123 | - Download: [dataset](https://drive.google.com/drive/folders/1jzYBuLPbxH4Wrp7CN1IJtoR_cMwm-5OK?usp=sharing) 124 | - Details: it contains 42 sets of images for image stitching. Many sets of images contain multiple images (> 2) for stitching. 125 | 126 | 127 | ### SEAGULL Dataset (2016) 128 | 129 | 130 |   image 131 | - Paper: [SEAGULL: Seam-Guided Local Alignment for Parallax-Tolerant Image Stitching](https://link.springer.com/chapter/10.1007/978-3-319-46487-9_23), ECCV2016 132 | - Project: No 133 | - Download: [dataset](https://drive.google.com/drive/folders/1_u5z4r7i8J4599v8ttNeXC8KJ8PiXV56?usp=sharing) 134 | - Details: it contains 24 pairs of images taken by the author using mobile phones with challenging parallax variation. 135 | 136 | 137 | ### REW Dataset (2018) 138 | 139 | 140 |   image 141 | - Paper: [Parallax-Tolerant Image Stitching Based on Robust Elastic Warping](https://ieeexplore.ieee.org/document/8119833), TMM2018 142 | - Project: [Official Code](https://github.com/gain2217/Robust_Elastic_Warping), [Python](https://github.com/breadcake/python-Robust_Elastic_Warping) 143 | - Download: [dataset](https://github.com/gain2217/Robust_Elastic_Warping) 144 | - Dataset: it contains two-view and multi-view image groups for image stitching. 145 | 146 | 147 | 148 | ### Dataset for Stitching with Multiple Registrations (2018) 149 | 150 | 151 |   image 152 | - Paper: [Robust Image Stitching with Multiple Registrations](https://drive.google.com/file/d/1BWdkiJJHBSn9JNaMVhhD1WHD8upK51AH/view), ECCV2018 153 | - Project: https://sites.google.com/view/oois-eccv18/home?authuser=0 154 | - Download: [dataset](https://drive.google.com/open?id=1RNfs8I9NZu6A2FGT6Ba86nfEBOgbPdSp) 155 | - Details: It contains 14 sets of images. 156 | 157 | 158 | ### Object-Centered Stitching Dataset (2018) 159 | 160 | 161 |   image 162 | - Paper: [Object-centered image stitching](https://drive.google.com/file/d/1_YnPNNWzNphdrd_51lXL7q-jm5N3Cttn/view), ECCV2018 163 | - Project: https://sites.google.com/view/oois-eccv18/home?authuser=0 164 | - Download: [dataset](https://drive.google.com/open?id=1OIDwCcmVlSMqrLmwPBA8G2A5G4NgcQMF) 165 | - Details: It contains 26 sets of images. 166 | 167 | 168 | ### BRAS Dataset (2019) 169 | 170 | 171 |   image 172 | - Paper: [Robust Alignment for Panoramic Stitching Via an Exact Rank Constraint](https://ieeexplore.ieee.org/abstract/document/8684316), TIP2019 173 | - Project: http://signal.ee.psu.edu/research/BRAS.html 174 | - Download: [dataset](http://signal.ee.psu.edu/research/BRAS.html) 175 | - Details: One group of catabus images 176 | 177 | 178 | ### SPW Dataset (2020) 179 | 180 | 181 |   image 182 | - Paper: [Single-Perspective Warps in Natural Image Stitching](https://arxiv.org/abs/1802.04645), TIP2020 183 | - Project: https://github.com/tlliao/Single-perspective-warps 184 | - Download: [dataset](https://github.com/tlliao/Single-perspective-warps/tree/master/Images) 185 | - Details: contains 42 sets of image pairs for stitching. 186 | 187 | 188 | ### VPG Dataset (2020) 189 | 190 | 191 |   image 192 | - Paper: [Vanishing Point Guided Natural Image Stitching](https://arxiv.org/pdf/2004.02478.pdf), arXiv2020 193 | - Project: http://cvrs.whu.edu.cn/projects/VPGStitching/ 194 | - Download: [dataset](https://drive.google.com/drive/folders/1n9Pf2vqNpT1r7QAjjYnVnwZu_OfuMRhW?usp=sharing) 195 | - Details: The dataset contains 36 sets of images, of which 12 sets of synthetic images and 24 sets of real images. All synthetic images were generated through 3Ds Max rendering hence the associated parameters are known. All real images were captured by a mobile phone. The VPG dataset contains both indoor scenes and outdoor street-view scenes. All images were carefully collected to ensure the Manhattan assumption. The number of images involved in stitching in each set ranges from 5 to 72. 196 | 197 | 198 | ### LPC Dataset (2021) 199 | 200 | 201 |   image 202 | - Paper: [Leveraging Line-point Consistence to Preserve Structures for Wide Parallax Image Stitching](https://openaccess.thecvf.com/content/CVPR2021/papers/Jia_Leveraging_Line-Point_Consistence_To_Preserve_Structures_for_Wide_Parallax_Image_CVPR_2021_paper.pdf), CVPR2021 203 | - Project: https://github.com/dut-media-lab/Image-Stitching 204 | - Download: [dataset](https://github.com/dut-media-lab/Image-Stitching/tree/main/Imgs) 205 | - Details: Add about 13 image pairs for image stitching. 206 | 207 | 208 | ### GES-50 (2022) 209 | 210 | 211 |   image 212 | - Paper: [Geometric Structure Preserving Warp for Natural Image Stitching](https://openaccess.thecvf.com/content/CVPR2022/html/Du_Geometric_Structure_Preserving_Warp_for_Natural_Image_Stitching_CVPR_2022_paper.html), CVPR2022 213 | - Project: https://github.com/flowerDuo/GES-GSP-Stitching 214 | - Download: [dataset](https://github.com/flowerDuo/GES-GSP-Stitching/tree/master/Dataset) 215 | - Details: There are 50 diversified and challenging image groups (26 from the previous dataset and 24 collected by this work). The number of images ranges from 2 to 35. 216 | 217 | 218 | 219 | 220 | ### Color Consistency Dataset (2019) 221 | 222 | 223 |   image 224 | - Paper: [A Closed-Form Solution for Multi-view Color Correction with Gradient Preservation](https://menghanxia.github.io/papers/2019_Color_Consistency_Optimization_isprs_journal.pdf), ISPRSJ2019 225 | - Project: https://github.com/MenghanXia/ColorConsistency 226 | - Download: [dataset](https://github.com/MenghanXia/ColorConsistency), [dataset](https://drive.google.com/drive/folders/1bXhFKNYrLVburN4l6q-nZfe7Vrq1YdyE?usp=sharing) 227 | - Details: It contains 3 sets of images for color correction in image stitching, including campus, lunchroom, and school building. 228 | 229 | 230 | ### OpenPano Dataset (2016) 231 | 232 | 233 |   image 234 | - Paper: Open-source panorama stitching program written in C++ from scratch. 235 | - Project: https://github.com/ppwwyyxx/OpenPano 236 | - Download: [dataset](https://github.com/ppwwyyxx/OpenPano/releases/tag/0.1) 237 | - Details: It contains 8 sets of images for panorama stitching, and the number of images for each set ranges from 4 to 38. 238 | 239 | 240 | ### Aerial Image Stitching (AIS) Dataset 241 | 242 | 243 | - Aerial Images of Virginia Beach: [Open Data Portal](https://gis.data.vbgov.com/datasets/824c57d560e648079cb4ed2ca763774c/explore) 244 | - OpenDroneMap Data: [ODMData](https://www.opendronemap.org/odm/datasets/) 245 | - PlanarMosaicking Data: [Paper-PR2017](https://www.sciencedirect.com/science/article/abs/pii/S0031320317300201), [Code](https://github.com/MenghanXia/AutoStitching), [Dataset](https://drive.google.com/drive/folders/1W5e4lWo7S3gfwyYh9lN3sxQ-YuU3W2Ly?usp=sharing) 246 | - UAVMosaicking Data: [Paper-RS2016](https://www.mdpi.com/2072-4292/8/3/204), [Dataset](https://drive.google.com/file/d/1sUI_iwCrwgMB4JKZff0wy0DLXY8A8d0c/view?usp=sharing) 247 | 248 | 249 | 250 | ## Deep Learning Image Stitching 251 | 252 | ### Hmg-dynamics (2020) 253 | 254 | 255 |   image 256 | - Paper: [Deep Homography Estimation for Dynamic Scenes](https://openaccess.thecvf.com/content_CVPR_2020/papers/Le_Deep_Homography_Estimation_for_Dynamic_Scenes_CVPR_2020_paper.pdf), CVPR2020 257 | - Project: https://github.com/lcmhoang/hmg-dynamics 258 | - Download: https://github.com/lcmhoang/hmg-dynamics 259 | - Details: Authors downloaded 877 videos with a Creative Commons License from YouTube. From these videos, they extracted 32,385 static video clips and then applied a known homography sequence to each of them to generate image/video pairs. 260 | 261 | 262 | ### Content-Aware-DeepH-Data (2020) 263 | 264 | 265 |   image 266 | - Paper: [Content-Aware Unsupervised Deep Homography Estimation](https://arxiv.org/pdf/1909.05983.pdf), ECCV2020 267 | - Project: https://github.com/JirongZhang/DeepHomography 268 | - Download: [dataset](https://drive.google.com/file/d/19d2ylBUPcMQBb_MNBBGl9rCAS7SU-oGm/view?usp=sharing) 269 | - Related Paper: [Semi-supervised Deep Large-baseline Homography Estimation with Progressive Equivalence Constraint](https://github.com/megvii-research/LBHomo), AAAI 2023 270 | - Details: The dataset contains 5 categories of a total of 80k image pairs, including regular (RE), low-texture (LT), low-light (LL), small-foregrounds (SF), and large-foregrounds (LF) scenes, with each category ≈16k image pairs. For the test data, 4.2k image pairs are randomly chosen from all categories. 271 | 272 | 273 | 274 | ### UDIS-D (2021) 275 | 276 | 277 |   image 278 | - Paper: [Unsupervised Deep Image Stitching: Reconstructing Stitched Features to Images](https://arxiv.org/abs/2106.12859), TIP2021 279 | - Project: https://github.com/nie-lang/UnsupervisedDeepImageStitching 280 | - Download: [dataset](https://github.com/nie-lang/UnsupervisedDeepImageStitching) 281 | - Related Paper: [Parallax-Tolerant Unsupervised Deep Image Stitching](https://arxiv.org/abs/2302.08207), ICCV2023, [[``Proj``]](https://github.com/nie-lang/UDIS2) 282 | - Details: It is an unsupervised deep image stitching dataset, including 10,440 cases for training and 1,106 for testing. 283 | 284 | 285 | ### DIR-D (2022) 286 | 287 | 288 |   image 289 | - Paper: [Deep Rectangling for Image Stitching: A Learning Baseline](https://arxiv.org/pdf/2203.03831.pdf), CVPR2022 290 | - Project: https://github.com/nie-lang/DeepRectangling 291 | - Download: [dataset](https://drive.google.com/file/d/1KR5DtekPJin3bmQPlTGP4wbM1zFR80ak/view?usp=sharing) 292 | - Details: DIR-D dataset with a wide range of irregular boundaries and scenes, which includes 5,839 samples for training and 519 samples for testing. Every image in the dataset has a resolution of 512×384. The DIR-D dataset is a synthesized dataset from the UDIS-D and MS-COCO datasets, in which each sample is a triplet consisting of a stitched image (I), a mask (M), and a rectangling label (R). 293 | 294 | 295 | ### WSSN Dataset (2022) 296 | 297 | 298 |   image 299 | - Paper: [Weakly-Supervised Stitching Network for Real-World Panoramic Image Generation](https://arxiv.org/abs/2209.05968), ECCV2022 300 | - Project: https://eadcat.github.io/WSSN/ 301 | - Download: [dataset](https://drive.google.com/file/d/1p27k77TWjknBYJ62EW97D2Xf_nElNZW3/view?usp=sharing), [code](https://github.com/EadCat/WeaklySupervisedStitchingNetwork) 302 | - Details: The dataset is a fisheye image dataset collected by a commercial VR camera called Kandao Obsidian R for image stitching. It can capture six fisheye images simultaneously using six lenses rotated at 60° intervals. Three fisheye images rotated by 0°, 120°, and 240° as inputs to the stitching model while the remaining three images rotated by 60°, 180°, and 300° are utilized as weak supervisions. In this dataset, 47,063 sets of images are used for the training and 1,400 for the test. Each training set includes three input fisheye images, three ERP images for weak supervision, and three masks. 303 | 304 | 305 | 306 | -------------------------------------------------------------------------------- /imgs/Contant-Aware-DeepH-Data.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/Contant-Aware-DeepH-Data.jpg -------------------------------------------------------------------------------- /imgs/DIR-D2022.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/DIR-D2022.png -------------------------------------------------------------------------------- /imgs/GES50_2022.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/GES50_2022.jpg -------------------------------------------------------------------------------- /imgs/LPC2021.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/LPC2021.jpg -------------------------------------------------------------------------------- /imgs/NISwGSP.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/NISwGSP.jpg -------------------------------------------------------------------------------- /imgs/REW.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/REW.png -------------------------------------------------------------------------------- /imgs/SPHP.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/SPHP.jpg -------------------------------------------------------------------------------- /imgs/SPW2020.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/SPW2020.jpg -------------------------------------------------------------------------------- /imgs/SVA2011.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/SVA2011.png -------------------------------------------------------------------------------- /imgs/UDIS-D.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/UDIS-D.png -------------------------------------------------------------------------------- /imgs/VPG2020.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/VPG2020.png -------------------------------------------------------------------------------- /imgs/WSSN2022.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/WSSN2022.png -------------------------------------------------------------------------------- /imgs/apap.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/apap.jpg -------------------------------------------------------------------------------- /imgs/bras.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/bras.png -------------------------------------------------------------------------------- /imgs/colorconsistency2019.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/colorconsistency2019.png -------------------------------------------------------------------------------- /imgs/hmg-dynamics-2020.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/hmg-dynamics-2020.png -------------------------------------------------------------------------------- /imgs/multi_regis.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/multi_regis.png -------------------------------------------------------------------------------- /imgs/object_center.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/object_center.png -------------------------------------------------------------------------------- /imgs/openpano.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/openpano.jpg -------------------------------------------------------------------------------- /imgs/parallax-tolerant_stitch.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/parallax-tolerant_stitch.jpg -------------------------------------------------------------------------------- /imgs/parallax-tolerant_stitch2.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/parallax-tolerant_stitch2.jpg -------------------------------------------------------------------------------- /imgs/seagull.jpg: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/seagull.jpg -------------------------------------------------------------------------------- /imgs/stereostitch_dataset.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/visionxiang/Image-Stitching-Dataset/1cb913b4141e896d8ba3a1291d88a776407ce9f6/imgs/stereostitch_dataset.png --------------------------------------------------------------------------------