{"id":13444407,"url":"https://github.com/XYZ-qiyh/Awesome-Learning-MVS","last_synced_at":"2025-03-20T18:32:39.825Z","repository":{"id":37637576,"uuid":"316390498","full_name":"XYZ-qiyh/Awesome-Learning-MVS","owner":"XYZ-qiyh","description":"📑 A list of awesome learning-based multi-view stereo papers","archived":false,"fork":false,"pushed_at":"2023-11-12T06:43:37.000Z","size":26795,"stargazers_count":525,"open_issues_count":0,"forks_count":58,"subscribers_count":19,"default_branch":"main","last_synced_at":"2024-05-23T04:02:01.800Z","etag":null,"topics":["multi-view-stereo","mvs","mvsnet","sfm","structure-from-motion"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/XYZ-qiyh.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2020-11-27T03:26:09.000Z","updated_at":"2024-05-20T07:44:52.000Z","dependencies_parsed_at":"2023-11-12T07:36:16.839Z","dependency_job_id":null,"html_url":"https://github.com/XYZ-qiyh/Awesome-Learning-MVS","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XYZ-qiyh%2FAwesome-Learning-MVS","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XYZ-qiyh%2FAwesome-Learning-MVS/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XYZ-qiyh%2FAwesome-Learning-MVS/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/XYZ-qiyh%2FAwesome-Learning-MVS/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/XYZ-qiyh","download_url":"https://codeload.github.com/XYZ-qiyh/Awesome-Learning-MVS/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":244670607,"owners_count":20491024,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["multi-view-stereo","mvs","mvsnet","sfm","structure-from-motion"],"created_at":"2024-07-31T04:00:22.209Z","updated_at":"2025-03-20T18:32:36.415Z","avatar_url":"https://github.com/XYZ-qiyh.png","language":null,"funding_links":[],"categories":["Uncategorized","PatchMatch-based MVS Methods","2020","Other Lists"],"sub_categories":["Uncategorized","Other Resources","TeX Lists"],"readme":"## Awesome-Learning-MVS (Methods and Datasets)\r\n\r\n\r\n### Learning-based MVS Methods\r\n1. Volumetric methods (SurfaceNet)\r\n2. Depthmap based methods (MVSNet/R-MVSNet and so on)\r\n\r\n( 💻 means code available)\r\n\r\n#### ICCV2017\r\n  + 💻 SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis [[paper](https://openaccess.thecvf.com/content_ICCV_2017/papers/Ji_SurfaceNet_An_End-To-End_ICCV_2017_paper.pdf)] [[Github](https://github.com/mjiUST/SurfaceNet)] [[T-PAMI](https://ieeexplore.ieee.org/document/9099504)]\r\n  + Learning a Multi-View Stereo Machine [[paper](https://papers.nips.cc/paper/2017/file/9c838d2e45b2ad1094d42f4ef36764f6-Paper.pdf)] (LSMs can produce two kinds of outputs - *voxel occupancy grids* decoded from 3D Grid or *per-view depth maps* decoded after a projection operation.)\r\n  + Learned Multi-Patch Similarity [[paper](https://openaccess.thecvf.com/content_ICCV_2017/papers/Hartmann_Learned_Multi-Patch_Similarity_ICCV_2017_paper.pdf)] [[supp](https://openaccess.thecvf.com/content_ICCV_2017/supplemental/Hartmann_Learned_Multi-Patch_Similarity_ICCV_2017_supplemental.pdf)] (Note: Learning to measure multi-image patch similiarity, NOT end-to-end learning MVS pipeline)\r\n\r\n#### CVPR2018\r\n+ 💻 DeepMVS: Learning Multi-view Stereopsis [[paper](https://openaccess.thecvf.com/content_cvpr_2018/papers/Huang_DeepMVS_Learning_Multi-View_CVPR_2018_paper.pdf)] [[project](https://phuang17.github.io/DeepMVS/index.html)] [[Github](https://github.com/phuang17/DeepMVS)]\r\n\r\n#### ECCV2018\r\n\r\n+ 💻 MVSNet: Depth Inference for Unstructured Multi-view Stereo [[paper](https://openaccess.thecvf.com/content_ECCV_2018/papers/Yao_Yao_MVSNet_Depth_Inference_ECCV_2018_paper.pdf)] [[supp](https://yoyo000.github.io/papers/yao2018mvsnet_supp.pdf)] [[Github](https://github.com/YoYo000/MVSNet)] \r\n\r\n#### CVPR2019\r\n\r\n+ 💻 Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference  [[paper](https://openaccess.thecvf.com/content_CVPR_2019/papers/Yao_Recurrent_MVSNet_for_High-Resolution_Multi-View_Stereo_Depth_Inference_CVPR_2019_paper.pdf)]  [[supp](https://openaccess.thecvf.com/content_CVPR_2019/supplemental/Yao_Recurrent_MVSNet_for_CVPR_2019_supplemental.pdf)] [[Github](https://github.com/YoYo000/MVSNet)]\r\n\r\n#### ICCV2019\r\n\r\n+ 💻 Point-Based Multi-View Stereo Network  [[paper](https://openaccess.thecvf.com/content_ICCV_2019/papers/Chen_Point-Based_Multi-View_Stereo_Network_ICCV_2019_paper.pdf)] [[supp](https://openaccess.thecvf.com/content_ICCV_2019/supplemental/Chen_Point-Based_Multi-View_Stereo_ICCV_2019_supplemental.pdf)] [[Github](https://github.com/callmeray/PointMVSNet)] [[T-PAMI](https://ieeexplore.ieee.org/abstract/document/9076298)] (Point-MVSNet performs multi-view stereo reconstruction in a *coarse-to-fine* fashion, learning to predict the 3D flow of each point to the groundtruth surface based on geometry priors and 2D image appearance cues)\r\n+ P-MVSNet: Learning Patch-wise Matching Confidence Aggregation for Multi-view Stereo [[paper](https://openaccess.thecvf.com/content_ICCV_2019/papers/Luo_P-MVSNet_Learning_Patch-Wise_Matching_Confidence_Aggregation_for_Multi-View_Stereo_ICCV_2019_paper.pdf)]\r\n+ MVSCRF: Learning Multi-view Stereo with Conditional Random Fields [[paper](https://openaccess.thecvf.com/content_ICCV_2019/papers/Xue_MVSCRF_Learning_Multi-View_Stereo_With_Conditional_Random_Fields_ICCV_2019_paper.pdf)]\r\n\r\n#### AAAI2020\r\n\r\n+ Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume [[paper](https://arxiv.org/pdf/1912.11746.pdf)] [[Github](https://github.com/GhiXu/CIDER)]\r\n\r\n#### CVPR2020\r\n\r\n+ 💻 Cascade Cost Volume for High-Resolutoin Multi-View Stereo and Stereo Matching [[paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Gu_Cascade_Cost_Volume_for_High-Resolution_Multi-View_Stereo_and_Stereo_Matching_CVPR_2020_paper.pdf)] [[Github](https://github.com/alibaba/cascade-stereo)] \r\n+ 💻 Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness [[paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Cheng_Deep_Stereo_Using_Adaptive_Thin_Volume_Representation_With_Uncertainty_Awareness_CVPR_2020_paper.pdf)] [[supp](https://openaccess.thecvf.com/content_CVPR_2020/supplemental/Cheng_Deep_Stereo_Using_CVPR_2020_supplemental.pdf)] [[Github](https://github.com/touristCheng/UCSNet)]\r\n\r\n+ 💻 Cost Volume Pyramid Based Depth Inference for Multi-View Stereo [[paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Yang_Cost_Volume_Pyramid_Based_Depth_Inference_for_Multi-View_Stereo_CVPR_2020_paper.pdf)] [[supp](https://openaccess.thecvf.com/content_CVPR_2020/supplemental/Yang_Cost_Volume_Pyramid_CVPR_2020_supplemental.pdf)] [[Github](https://github.com/JiayuYANG/CVP-MVSNet)]\r\n\r\n+ 💻 Fast-MVSNet: Sparse-to-Dense Multi-View Stereo with Learned Propagation and Gauss-Newton Refinement [[paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Yu_Fast-MVSNet_Sparse-to-Dense_Multi-View_Stereo_With_Learned_Propagation_and_Gauss-Newton_Refinement_CVPR_2020_paper.pdf)] [[supp](https://openaccess.thecvf.com/content_CVPR_2020/supplemental/Yu_Fast-MVSNet_Sparse-to-Dense_Multi-View_CVPR_2020_supplemental.pdf)] [[Github](https://github.com/svip-lab/FastMVSNet)] \r\n\r\n+ Attention-Aware Multi-View Stereo [[paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Luo_Attention-Aware_Multi-View_Stereo_CVPR_2020_paper.pdf)]\r\n\r\n+ 💻 A Novel Recurrent Encoder-Decoder Structure for Large-Scale Multi-view Stereo Reconstruction from An Open Aerial Dataset [[paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Liu_A_Novel_Recurrent_Encoder-Decoder_Structure_for_Large-Scale_Multi-View_Stereo_Reconstruction_CVPR_2020_paper.pdf)] [[Github](https://github.com/gpcv-liujin/REDNet)] [[data](http://gpcv.whu.edu.cn/data/WHU_MVS_Stereo_dataset.html)]\r\n\r\n\r\n#### ECCV2020\r\n\r\n+ 💻 Pyramid Multi-view Stereo Net with Self-adaptive View aggregation [[paper](https://www.ecva.net/papers/eccv_2020/papers_ECCV/papers/123540732.pdf)] [[Github](https://github.com/yhw-yhw/PVAMVSNet)]\r\n+ 💻 Dense Hybird Recurrent Multi-view Stereo Net with Dynamic Consistency Checking [[paper](https://deepai.org/publication/dense-hybrid-recurrent-multi-view-stereo-net-with-dynamic-consistency-checking)] [[Github](https://github.com/yhw-yhw/D2HC-RMVSNet)]\r\n\r\n\r\n#### BMVC2020\r\n+ 💻 Visibility-aware Multi-view Stereo Network [[paper](https://arxiv.org/abs/2008.07928)] [[Github](https://github.com/jzhangbs/Vis-MVSNet)]\r\n\r\n#### WACV2021\r\n+ Long-range Attention Network for Multi-View Stereo [[paper](https://openaccess.thecvf.com/content/WACV2021/papers/Zhang_Long-Range_Attention_Network_for_Multi-View_Stereo_WACV_2021_paper.pdf)]\r\n\r\n#### CVPR2021\r\n+ 💻 PatchmatchNet: Learned Multi-View Patchmatch Stereo [[paper](https://arxiv.org/pdf/2012.01411.pdf)] [[Github](https://github.com/FangjinhuaWang/PatchmatchNet)]\r\n\r\n#### ICCV2021\r\n+ 💻 AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network [[paper](https://openaccess.thecvf.com/content/ICCV2021/papers/Wei_AA-RMVSNet_Adaptive_Aggregation_Recurrent_Multi-View_Stereo_Network_ICCV_2021_paper.pdf)] [[supp](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Wei_AA-RMVSNet_Adaptive_Aggregation_ICCV_2021_supplemental.pdf)] [[Github](https://github.com/QT-Zhu/AA-RMVSNet)]\r\n+ EPP-MVSNet: Epipolar-Assembling Based Depth Prediction for Multi-View Stereo [[paper](https://openaccess.thecvf.com/content/ICCV2021/papers/Ma_EPP-MVSNet_Epipolar-Assembling_Based_Depth_Prediction_for_Multi-View_Stereo_ICCV_2021_paper.pdf)]\r\n+ Just a Few Points are All You Need for Multi-view Stereo: A Novel Semi-supervised Learning Method for Multi-view Stereo [[paper](https://openaccess.thecvf.com/content/ICCV2021/papers/Kim_Just_a_Few_Points_Are_All_You_Need_for_Multi-View_ICCV_2021_paper.pdf)] [[supp](https://openaccess.thecvf.com/content/ICCV2021/supplemental/Kim_Just_a_Few_ICCV_2021_supplemental.pdf)]\r\n\r\n#### 3DV 2021\r\n+ 💻 Deep Multi-View Stereo gone wild. [[paper](https://arxiv.org/abs/2104.15119v2)]  [[Project](https://imagine.enpc.fr/~darmonf/wild_deep_mvs/)] [[Github](https://github.com/fdarmon/wild_deep_mvs)]\r\n\r\n#### CVPR 2022\r\n+ 💻 IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo [[paper](https://openaccess.thecvf.com/content/CVPR2022/papers/Wang_IterMVS_Iterative_Probability_Estimation_for_Efficient_Multi-View_Stereo_CVPR_2022_paper.pdf)] [[supp](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Wang_IterMVS_Iterative_Probability_CVPR_2022_supplemental.pdf)] [[Github](https://github.com/FangjinhuaWang/IterMVS)]\r\n+ 💻 Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation and Focal Loss [[paper](https://openaccess.thecvf.com/content/CVPR2022/papers/Peng_Rethinking_Depth_Estimation_for_Multi-View_Stereo_A_Unified_Representation_CVPR_2022_paper.pdf)][[supp](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Peng_Rethinking_Depth_Estimation_CVPR_2022_supplemental.pdf)] [[Github](https://github.com/prstrive/UniMVSNet)]\r\n+ 💻 RayMVSNet: Learning Ray-Based 1D Implicit Fields for Accurate Multi-View Stereo [[paper](https://openaccess.thecvf.com/content/CVPR2022/papers/Xi_RayMVSNet_Learning_Ray-Based_1D_Implicit_Fields_for_Accurate_Multi-View_Stereo_CVPR_2022_paper.pdf)] [[supp](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Xi_RayMVSNet_Learning_Ray-Based_CVPR_2022_supplemental.pdf)] [[Github](https://github.com/Airobin329/RayMVSNet)]\r\n+ Non-Parametric Depth Distribution Modelling Based Depth Inference for Multi-View Stereo [[paper](https://openaccess.thecvf.com/content/CVPR2022/papers/Yang_Non-Parametric_Depth_Distribution_Modelling_Based_Depth_Inference_for_Multi-View_Stereo_CVPR_2022_paper.pdf)] [[supp](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Yang_Non-Parametric_Depth_Distribution_CVPR_2022_supplemental.pdf)]\r\n+ 💻 TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers [[paper](https://openaccess.thecvf.com/content/CVPR2022/papers/Ding_TransMVSNet_Global_Context-Aware_Multi-View_Stereo_Network_With_Transformers_CVPR_2022_paper.pdf)] [[supp](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Ding_TransMVSNet_Global_Context-Aware_CVPR_2022_supplemental.pdf)] [[Github](https://github.com/MegviiRobot/TransMVSNet)]\r\n\r\n+ 💻 Generalized Binary Search Network for Highly-Efficient Multi-View Stereo [[paper](https://openaccess.thecvf.com/content/CVPR2022/papers/Mi_Generalized_Binary_Search_Network_for_Highly-Efficient_Multi-View_Stereo_CVPR_2022_paper.pdf)] [[supp](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Mi_Generalized_Binary_Search_CVPR_2022_supplemental.pdf)] [[Github](https://github.com/MiZhenxing/GBi-Net)]\r\n+ 💻 Efficient Multi-View Stereo by Iterative Dynamic Cost Volume [[paper](https://openaccess.thecvf.com/content/CVPR2022/papers/Wang_Efficient_Multi-View_Stereo_by_Iterative_Dynamic_Cost_Volume_CVPR_2022_paper.pdf)] [[supp](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Wang_Efficient_Multi-View_Stereo_CVPR_2022_supplemental.pdf)] [[Github](https://github.com/bdwsq1996/Effi-MVS)]\r\n+ 💻 MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions [[paper](https://openaccess.thecvf.com/content/CVPR2022/papers/Yang_MVS2D_Efficient_Multi-View_Stereo_via_Attention-Driven_2D_Convolutions_CVPR_2022_paper.pdf)] [[supp](https://openaccess.thecvf.com/content/CVPR2022/supplemental/Yang_MVS2D_Efficient_Multi-View_CVPR_2022_supplemental.pdf)] [[Github](https://github.com/zhenpeiyang/MVS2D)]\r\n\r\n#### ECCV 2022\r\n+ 💻 MVSTER: Epipolar Transformer for Efficient Multi-View Stereo [[paper](https://arxiv.org/abs/2204.07346)] [[Github](https://github.com/JeffWang987/MVSTER)]\r\n+ 💻 Multiview Stereo with Cascaded Epipolar RAFT [[paper](https://arxiv.org/abs/2205.04502)] [[Github](https://github.com/princeton-vl/CER-MVS)]\r\n\r\n\r\n#### Journal Paper\r\n\r\n+ MVSNet++: Learning Depth-Based Attention Pyramid Features for Multi-View Stereo. IEEE Transactions on Image Processing [[paper](https://ieeexplore.ieee.org/document/9115828)]\r\n+ HighRes-MVSNet: A Fast Multi-View Stereo Network for Dense 3D Reconstruction From High-Resolution Images. IEEE Access [[paper](https://ieeexplore.ieee.org/document/9319163)]\r\n+ 💻 AACVP-MVSNet: Attention-aware cost volume pyramid based multi-view stereo network for 3D reconstruction. ISPRS Journal of Photogrammetry and Remote Sensing [[paper](https://www.sciencedirect.com/science/article/pii/S0924271621000794)] [[Github](https://github.com/ArthasMil/AACVP-MVSNet)]\r\n+ Learning Inverse Depth Regression for Pixelwise Visibility-Aware Multi-View Stereo Networks. International Journal of Computer Vision [[paper](https://trebuchet.public.springernature.app/get_content/79aa1569-1998-49c9-b675-acb305d056a2)]\r\n+ Sparse prior guided deep multi-view stereo. Computers \u0026 Graphics [[paper](https://www.sciencedirect.com/science/article/abs/pii/S0097849322001157)]\r\n\r\n\r\n### ~~To Be Continued~~\r\n\r\n#### Survey Paper\r\n+ A Survey on Deep Learning Techniques for Stereo-based Depth Estimation. IEEE T-PAMI [[ArXiv](https://arxiv.org/abs/2006.02535)] [[IEEE Xplore](https://ieeexplore.ieee.org/document/9233988)]\r\n+ Deep Learning for Multi-view Stereo via Plane Sweep: A Survey [[paper](https://arxiv.org/abs/2106.15328)]\r\n+ Multi-view stereo in the Deep Learning Era: A comprehensive review [[paper](https://www.sciencedirect.com/science/article/pii/S0141938221001062)]\r\n\r\n\r\n\u003c!--\r\n#### ArXiv Paper\r\n+ PVSNet: Pixelwise Visibility-Aware Multi-View Stereo Network [[paper](https://arxiv.org/abs/2007.07714)]\r\n+ DDR-Net: Learning Multi-Stage Multi-View Stereo With Dynamic Depth Range [[paper](https://arxiv.org/abs/2103.14275)]  [[Github](https://github.com/Tangshengku/DDR-Net)]\r\n+ Non-local Recurrent Regularization Networks for Multi-view Stereo [[paper](https://arxiv.org/abs/2110.06436)]\r\n---\u003e\r\n\r\n#### PhD Thesis\r\n+ 🎓 [Robust Methods for Accurate and Efficient 3D Modeling from Unstructured Imagery](https://www.research-collection.ethz.ch/handle/20.500.11850/295763), Johannes L. Schönberger@ETH Zürich\r\n+ 🎓 Learning Large-scale Multi-view Stereopsis, Yao Yao@HKUST\r\n\r\n\r\n\r\n### Multi-view Stereo Benchmark\r\n\r\n+ **Middlebury** [CVPR06']\r\n  + A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms [[paper](https://vision.middlebury.edu/mview/seitz_mview_cvpr06.pdf)] [[website](https://vision.middlebury.edu/mview/)]\r\n\r\n+ **EPFL** [CVPR08']\r\n  + On Benchmarking Camera Calibration and Multi-View Stereo for High Resolution Imagery [[paper](https://infoscience.epfl.ch/record/126393)]\r\n \u003c!-- [Strecha] [Fountain] --\u003e\r\n\r\n+ **DTU** [CVPR2014, IJCV2016]\r\n  + Large-scale data for multiple-view stereopsis [paper: [CVPR2014](https://roboimagedata2.compute.dtu.dk/data/text/multiViewCVPR2014.pdf), [IJCV2016](https://link.springer.com/content/pdf/10.1007/s11263-016-0902-9.pdf)] [[website](http://roboimagedata.compute.dtu.dk/?page_id=36)] [[Eval code](https://github.com/Todd-Qi/MVSNet-PyTorch/tree/master/evaluations/dtu)] [[video](https://www.bilibili.com/video/BV1k5411G7NA/)]\r\n\r\n+ **Tanks and Temples** [ACM ToG2017]\r\n  + Tanks and Temples: Benchmarking Large-Scale Scene Reconstruction  [[paper](https://docs.google.com/uc?export=download\u0026id=0B-ePgl6HF260bGJkdFBCemRLZGM)] [[supp](https://docs.google.com/uc?export=download\u0026id=0B-ePgl6HF260MGhQX0dCcmdHbFk)] [[website](https://www.tanksandtemples.org/)] [[Github](https://github.com/intel-isl/TanksAndTemples)] [[leaderboard](https://www.tanksandtemples.org/leaderboard/)]\r\n\r\n+ **ETH3D** [CVPR2017]\r\n  + A Multi-View Stereo Benchmark with High-Resolution Images and Multi-Camera Videos [[paper](https://www.eth3d.net/data/schoeps2017cvpr.pdf)] [[supp](https://www.eth3d.net/data/schoeps2017cvpr-supp.pdf)] [[website](https://www.eth3d.net/)] [[Github](https://github.com/ETH3D)]\r\n\r\n+ **BlendedMVS** [CVPR2020]\r\n  + BlendedMVS: A Large-Scale Dataset for Generalized Multi-View Stereo Network [[paper](https://openaccess.thecvf.com/content_CVPR_2020/papers/Yao_BlendedMVS_A_Large-Scale_Dataset_for_Generalized_Multi-View_Stereo_Networks_CVPR_2020_paper.pdf)] [[supp](https://openaccess.thecvf.com/content_CVPR_2020/supplemental/Yao_BlendedMVS_A_Large-Scale_CVPR_2020_supplemental.pdf)] [[Github](https://github.com/YoYo000/BlendedMVS)] [[visual](https://github.com/kwea123/BlendedMVS_scenes)] \r\n\r\n+ **GigaMVS** [T-PAMI2021]\r\n  + GigaMVS: A Benchmark for Ultra-large-scale Gigapixel-level 3D Reconstruction [[paper](https://ieeexplore.ieee.org/document/9547729)] [[website](http://www.gigamvs.com/)]\r\n\r\n+ **Multi-sensor large-scale dataset for multi-view 3D reconstruction** [CVPR2023]\r\n  + Multi-sensor large-scale dataset for multi-view 3D reconstruction [[paper](https://openaccess.thecvf.com/content/CVPR2023/papers/Voynov_Multi-Sensor_Large-Scale_Dataset_for_Multi-View_3D_Reconstruction_CVPR_2023_paper.pdf)] [[website](https://skoltech3d.appliedai.tech/)]\r\n\r\n\r\n### Large-scale Real-world Scenes\r\n1. Chinese Style Architectures\r\n  + http://vision.ia.ac.cn/zh/data/index.html, provided by CASIA.\r\n\r\n2. Western Style Architectures\r\n  + https://colmap.github.io/datasets.html, provided by COLMAP.\r\n  + [ImageDataset_SceauxCastle](https://github.com/openMVG/ImageDataset_SceauxCastle), provided by OpenMVG.\r\n\r\n3. Aerial Dataset\r\n  + http://gpcv.whu.edu.cn/data/WHU_MVS_Stereo_dataset.html, provided by WHU.\r\n\r\n\r\n\r\n### Other similar collections\r\n+ [Awesome-MVS1](https://github.com/walsvid/Awesome-MVS)\r\n+ [Awesome-MVS2](https://github.com/krahets/awesome-mvs)\r\n+ [PatchMatch Multi-view Stereo](https://github.com/XYZ-qiyh/PatchMatch-Multi-view-Stereo)\r\n+ [Unsupervised Multi-view Stereo](https://github.com/XYZ-qiyh/Awesome-Learning-MVS/blob/main/UnsupMVS.md)\r\n+ [multi-view-3d-reconstruction](https://github.com/XYZ-qiyh/multi-view-3d-reconstruction)\r\n\r\n### Future works (Personal Perspective)\r\n+ ultra-large-scale 3D Reconstruction: [GigaMVS](https://github.com/THU-luvision/GigaMVS)\r\n+ Semantic multi-view 3D Reconstruction\r\n\r\n\r\n### 部分论文讲解\r\n如果想看经典MVS论文介绍，可以参照👉[中文论文讲解](MVS_Summary.md)\r\n\r\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FXYZ-qiyh%2FAwesome-Learning-MVS","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FXYZ-qiyh%2FAwesome-Learning-MVS","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FXYZ-qiyh%2FAwesome-Learning-MVS/lists"}