MVS数据集论文下载 （DTU数据集、Tanks and Temples 数据集、ETH3D 数据集、BlendedMVS数据集

# BlendedMVS ## About [BlendedMVS](https://arxiv.org/abs/1911.10127) is a large-scale MVS dataset for generalized multi-view stereo networks. The dataset contains 17k MVS training samples covering a variety of 113 scenes, including architectures, sculptures and small objects. #BlendedMVS是广义多视点立体网络的大规模MVS数据集。数据集包含17k MVS训练样本，涵盖113种场景，包括建筑、雕塑和小物体。 <a href="https://www.altizure.com/project-model?pid=5bfe5ae0fe0ea555e6a969ca"><img src="doc/cover0.gif" width="425"></a> <a href="https://www.altizure.com/project-model?pid=58eaf1513353456af3a1682a"><img src="doc/cover1.gif" width="425"></a> <a href="https://www.altizure.com/project-model?pid=5c34529873a8df509ae57b58"><img src="doc/cover2.gif" width="425"></a> <a href="https://www.altizure.com/project-model?pid=57f8d9bbe73f6760f10e916a"><img src="doc/cover3.gif" width="425"></a> ## Upgrade to BlendedMVG BlendedMVG, a superset of [BlendedMVS](https://arxiv.org/abs/1911.10127), is a multi-purpose large-scale dataset for solving multi-view geometry related problems. Except for the 113 scenes in BlendedMVS dataset, we follow its blending procedure to generate 389 more scenes (originally shown in [GL3D](https://github.com/lzx551402/GL3D)) for BlendedMVG. The training image number is increased from 17k to over 110k. #BlendedMVG是[BlendedMVS]的超集，是一个用于解决多视图几何相关问题的多用途大规模数据集。除了BlendedMVS数据集中的113个场景外，我们按照它的混合过程为BlendedMVG生成了389个场景(最初显示在[GL3D]中)。训练图像数量从17k增加到超过110k。 BlendedMVG and its preceding works ([BlendedMVS](https://arxiv.org/abs/1911.10127) and [GL3D](https://github.com/lzx551402/GL3D)) have been applied to several key 3D computer vision tasks, including image retrieval, image feature detection and description, two-view outlier rejection and multi-view stereo. If you find BlendedMVS or BlendedMVG useful for your research, please cite: #BlendedMVG及其之前的工作([BlendedMVS]和[GL3D])已应用于多个关键的三维计算机视觉任务，包括图像检索、图像特征检测与描述、双视图异常值抑制和多视图立体。如果您发现BlendedMVS或BlendedMVG对您的研究有用，请引用: ``` @article{yao2020blendedmvs,   title={BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks},   author={Yao, Yao and Luo, Zixin and Li, Shiwei and Zhang, Jingyang and Ren, Yufan and Zhou, Lei and Fang, Tian and Quan, Long},   journal={Computer Vision and Pattern Recognition (CVPR)},   year={2020} } ``` ## License <a rel="license" href="http://creativecommons.org/licenses/by/4.0/"><img alt="Creative Commons License" style="border-width:0" src="https://i.creativecommons.org/l/by/4.0/88x31.png" /></a><br /><span xmlns:dct="http://purl.org/dc/terms/" href="http://purl.org/dc/dcmitype/Dataset" property="dct:title" rel="dct:type">BlendedMVS and BlendedMVG</span> are licensed under a <a rel="license" href="http://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution 4.0 International License</a>!!! ## Download #对于MVS网络，BlendedMVG被预处理并分成3个更小的子集(BlendedMVS, BlendedMVS+和BlendedMVS++): For MVS networks, BlendedMVG is preprocessed and split into 3 smaller subsets (BlendedMVS, BlendedMVS+ and BlendedMVS++): |Dataset         | Resolution (768 x 576) | Resolution (2048 x 1536) | Supplementaries | |:--------------:|:---------------:|:----------------------------------:|:---------------:| |BlendedMVS      |      [low-res set](https://1drv.ms/u/s!Ag8Dbz2Aqc81gVDu7FHfbPZwqhIy?e=BHY07t) (27.5 GB)    | [high-res set](https://1drv.ms/u/s!Ag8Dbz2Aqc81ezb9OciQ4zKwJ_w?e=afFOTi) (156 GB)    | [textured meshes](https://1drv.ms/u/s!Ag8Dbz2Aqc81fkvi2X9Mmzan0FI?e=7x2WoS) (9.42 GB), [other images](https://1drv.ms/u/s!Ag8Dbz2Aqc81gVMgQoHpAJP4jlwo?e=wVOWqD) (7.56 GB) | |BlendedMVS+|[low-res set](https://1drv.ms/u/s!Ag8Dbz2Aqc81gVLILxpohZLEYiIa?e=MhwYSR) (81.5 GB)        | -    |   - | |BlendedMVS++|[low-res set](https://1drv.ms/u/s!Ag8Dbz2Aqc81gVHCxmURGz0UBGns?e=Tnw2KY) (80.0 GB)  | -   |   -    | Experiments in [BlendedMVS paper](https://arxiv.org/abs/1911.10127) were conducting using the BlendedMVS low-res-dataset. In most cases, the low-res dataset would be enough. #BlendedMVS论文中的实验是使用BlendedMVS低分辨率数据集进行的。在大多数情况下，低分辨率数据集就足够了。 ## Dataset Structure BlendedMVS(G) dataset adopts MVSNet input format. Please structure your dataset as listed below after downloading the whole dataset: #BlendedMVS(G)数据集采用MVSNet输入格式。下载整个数据集后，请按照下面列出的方式构建数据集: ``` DATA_ROOT                 ├── BlendedMVG_list.txt                 ├── BlendedMVS_list.txt                 ├── BlendedMVS+_list.txt                 ├── BlendedMVS++_list.txt               ├── ... ├── PID0                         │   ├── blended_images           │   │ ├── 00000000.jpg         │   │ ├── 00000000_masked.jpg         │   │ ├── 00000001.jpg         │   │ ├── 00000001_masked.jpg         │   │ └── ...                 │   ├── cams                       │   │   ├── pair.txt           │   │   ├── 00000000_cam.txt     │   │   ├── 00000001_cam.txt     │   │   └── ...                 │   └── rendered_depth_maps     │       ├── 00000000.pfm         │     ├── 00000001.pfm         │     └── ...                     ├── PID1                         ├── ...                         └── PID501     ``` ``PID`` here is the unique project ID listed in the ``BlendedMVG_list.txt`` file. We provide blended images with and without masks.  For detailed file formats, please refer to [MVSNet](https://github.com/YoYo000/MVSNet). #' ' PID ' '这里是' ' BlendedMVG_list.txt ' '文件中列出的唯一项目ID。我们提供带有和不带有掩码的混合图像。详细文件格式请参考[MVSNet](https://github.com/YoYo000/MVSNet)。 ## What you can do with BlendedMVS(G)? Please refer to following repositories on how to apply BlendedMVS(G) on multi-view stereo and feature detector/descriptor networks: #关于如何在多视图立体和特征检测器/描述符网络上应用BlendedMVS(G)，请参考以下存储库: |Tasks            |Repositories                                           | |:--------------:|:--------------------------------------------------:| |Multi-view stereo | [MVSNet & R-MVSNet](https://github.com/YoYo000/MVSNet) | |Descriptors & Detectors| [GL3D](https://github.com/lzx551402/GL3D) & [ASLFeat](https://github.com/lzx551402/ASLFeat) & [ContextDesc](https://github.com/lzx551402/contextdesc) & [GeoDesc](https://github.com/lzx551402/geodesc)  | Except for the above tasks, we believe BlendedMVS(G) could also be applied to a variety of geometry related problems, including, but not limited to: #除了上述任务，我们认为BlendedMVS(G)还可以应用于各种与几何相关的问题，包括但不限于: * Sparse outlier rejection ([OANet](https://github.com/zjhthu/OANet), tested with the original GL3D) * Image retrieval ([MIRorR](https://github.com/hlzz/mirror), tested with the original GL3D) * Single-view depth/normal estimation * Two-view disparity estimation * Single/multi-view camera pose regression #稀疏异常值剔除([OANet]，用原始GL3D测试) #图像检索([MIRorR]，用原始GL3D测试) #单视图深度/正态估计 #两视图视差估