Awesome Learning MVS Save Abandoned

๐Ÿ“‘ A list of awesome learning-based multi-view stereo papers

Project README

Awesome-Learning-MVS (Methods and Datasets)

Learning-based MVS Methods

  1. Volumetric methods (SurfaceNet)
  2. Depthmap based methods (MVSNet/R-MVSNet and so on)

( ๐Ÿ’ป means code available)

ICCV2017

  • ๐Ÿ’ป SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis [paper] [Github] [T-PAMI]
  • Learning a Multi-View Stereo Machine [paper] (LSMs can produce two kinds of outputs - voxel occupancy grids decoded from 3D Grid or per-view depth maps decoded after a projection operation.)
  • Learned Multi-Patch Similarity [paper] [supp] (Note: Learning to measure multi-image patch similiarity, NOT end-to-end learning MVS pipeline)

CVPR2018

ECCV2018

  • ๐Ÿ’ป MVSNet: Depth Inference for Unstructured Multi-view Stereo [paper] [supp] [Github]

CVPR2019

  • ๐Ÿ’ป Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference [paper] [supp] [Github]

ICCV2019

  • ๐Ÿ’ป Point-Based Multi-View Stereo Network [paper] [supp] [Github] [T-PAMI] (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)
  • P-MVSNet: Learning Patch-wise Matching Confidence Aggregation for Multi-view Stereo [paper]
  • MVSCRF: Learning Multi-view Stereo with Conditional Random Fields [paper]

AAAI2020

  • Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume [paper] [Github]

CVPR2020

  • ๐Ÿ’ป Cascade Cost Volume for High-Resolutoin Multi-View Stereo and Stereo Matching [paper] [Github]

  • ๐Ÿ’ป Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness [paper] [supp] [Github]

  • ๐Ÿ’ป Cost Volume Pyramid Based Depth Inference for Multi-View Stereo [paper] [supp] [Github]

  • ๐Ÿ’ป Fast-MVSNet: Sparse-to-Dense Multi-View Stereo with Learned Propagation and Gauss-Newton Refinement [paper] [supp] [Github]

  • Attention-Aware Multi-View Stereo [paper]

  • ๐Ÿ’ป A Novel Recurrent Encoder-Decoder Structure for Large-Scale Multi-view Stereo Reconstruction from An Open Aerial Dataset [paper] [Github] [data]

ECCV2020

  • ๐Ÿ’ป Pyramid Multi-view Stereo Net with Self-adaptive View aggregation [paper] [Github]
  • ๐Ÿ’ป Dense Hybird Recurrent Multi-view Stereo Net with Dynamic Consistency Checking [paper] [Github]

BMVC2020

  • ๐Ÿ’ป Visibility-aware Multi-view Stereo Network [paper] [Github]

WACV2021

  • Long-range Attention Network for Multi-View Stereo [paper]

CVPR2021

  • ๐Ÿ’ป PatchmatchNet: Learned Multi-View Patchmatch Stereo [paper] [Github]

ICCV2021

  • ๐Ÿ’ป AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network [paper] [supp] [Github]
  • EPP-MVSNet: Epipolar-Assembling Based Depth Prediction for Multi-View Stereo [paper]
  • Just a Few Points are All You Need for Multi-view Stereo: A Novel Semi-supervised Learning Method for Multi-view Stereo [paper] [supp]

3DV 2021

CVPR 2022

  • ๐Ÿ’ป IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo [paper] [supp] [Github]

  • ๐Ÿ’ป Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation and Focal Loss [paper][supp] [Github]

  • ๐Ÿ’ป RayMVSNet: Learning Ray-Based 1D Implicit Fields for Accurate Multi-View Stereo [paper] [supp] [Github]

  • Non-Parametric Depth Distribution Modelling Based Depth Inference for Multi-View Stereo [paper] [supp]

  • ๐Ÿ’ป TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers [paper] [supp] [Github]

  • ๐Ÿ’ป Generalized Binary Search Network for Highly-Efficient Multi-View Stereo [paper] [supp] [Github]

  • ๐Ÿ’ป Efficient Multi-View Stereo by Iterative Dynamic Cost Volume [paper] [supp] [Github]

  • ๐Ÿ’ป MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions [paper] [supp] [Github]

ECCV 2022

  • ๐Ÿ’ป MVSTER: Epipolar Transformer for Efficient Multi-View Stereo [paper] [Github]
  • ๐Ÿ’ป Multiview Stereo with Cascaded Epipolar RAFT [paper] [Github]

Journal Paper

  • MVSNet++: Learning Depth-Based Attention Pyramid Features for Multi-View Stereo. IEEE Transactions on Image Processing [paper]
  • HighRes-MVSNet: A Fast Multi-View Stereo Network for Dense 3D Reconstruction From High-Resolution Images. IEEE Access [paper]
  • ๐Ÿ’ป AACVP-MVSNet: Attention-aware cost volume pyramid based multi-view stereo network for 3D reconstruction. ISPRS Journal of Photogrammetry and Remote Sensing [paper] [Github]
  • Learning Inverse Depth Regression for Pixelwise Visibility-Aware Multi-View Stereo Networks. International Journal of Computer Vision [paper]

To Be Continued

Survey Paper

  • A Survey on Deep Learning Techniques for Stereo-based Depth Estimation. IEEE T-PAMI [ArXiv] [IEEE Xplore]
  • Deep Learning for Multi-view Stereo via Plane Sweep: A Survey [paper]
  • Multi-view stereo in the Deep Learning Era: A comprehensive review [paper]

PhD Thesis

Multi-view Stereo Benchmark

  • Middlebury [CVPR06']

    • A Comparison and Evaluation of Multi-View Stereo Reconstruction Algorithms [paper] [website]
  • EPFL [CVPR08']

    • On Benchmarking Camera Calibration and Multi-View Stereo for High Resolution Imagery [paper]
  • DTU [CVPR2014, IJCV2016]

  • Tanks and Temples [ACM ToG2017]

  • ETH3D [CVPR2017]

    • A Multi-View Stereo Benchmark with High-Resolution Images and Multi-Camera Videos [paper] [supp] [website] [Github]
  • BlendedMVS [CVPR2020]

    • BlendedMVS: A Large-Scale Dataset for Generalized Multi-View Stereo Network [paper] [supp] [Github] [visual]
  • GigaMVS [T-PAMI2021]

    • GigaMVS: A Benchmark for Ultra-large-scale Gigapixel-level 3D Reconstruction [paper] [website]
  • Multi-sensor large-scale dataset for multi-view 3D reconstruction [ArXiv2022]

    • Multi-sensor large-scale dataset for multi-view 3D reconstruction [paper] [website]

Large-scale Real-world Scenes

  1. Chinese Style Architectures
  1. Western Style Architectures
  1. Aerial Dataset

Other similar collections

Future works (Personal Perspective)

  • ultra-large-scale 3D Reconstruction: GigaMVS
  • Semantic multi-view 3D Reconstruction

้ƒจๅˆ†่ฎบๆ–‡่ฎฒ่งฃ

ๅฆ‚ๆžœๆƒณ็œ‹็ปๅ…ธMVS่ฎบๆ–‡ไป‹็ป๏ผŒๅฏไปฅๅ‚็…ง๐Ÿ‘‰ไธญๆ–‡่ฎบๆ–‡่ฎฒ่งฃ

Open Source Agenda is not affiliated with "Awesome Learning MVS" Project. README Source: XYZ-qiyh/Awesome-Learning-MVS
Stars
328
Open Issues
0
Last Commit
1 year ago

Open Source Agenda Badge

Open Source Agenda Rating