mlsanityData to 14 Oct 2026

Learning-based Multi-View Stereo: A Survey

arXiv 2408.15235 ↗First posted 27 Aug 2024cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

3D reconstruction aims to recover the dense 3D structure of a scene. It plays an essential role in various applications such as Augmented/Virtual Reality (AR/VR), autonomous driving and robotics. Leveraging multiple views of a scene captured from different viewpoints, Multi-View Stereo (MVS) algorithms synthesize a comprehensive 3D representation, enabling precise reconstruction in complex environments. Due to its efficiency and effectiveness, MVS has become a pivotal method for image-based 3D reconstruction. Recently, with the success of deep learning, many learning-based MVS methods have been proposed, achieving impressive performance against traditional methods. We categorize these learning-based methods as: depth map-based, voxel-based, NeRF-based, 3D Gaussian Splatting-based, and large feed-forward methods. Among these, we focus significantly on depth map-based methods, which are the main family of MVS due to their conciseness, flexibility and scalability. In this survey, we provide a comprehensive review of the literature at the time of this writing. We investigate these learning-based methods, summarize their performances on popular benchmarks, and discuss promising future research directions in this area.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 172 of its 261 references that are in the map. First posted on arXiv 27 Aug 2024.

Builds on

172 of 261 references.

References · 172

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  5. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  6. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  7. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  8. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  9. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  10. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  11. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  12. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
38 more
  1. 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  3. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  4. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  5. 2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
  6. 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
  7. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  8. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  9. 2017Deformable Convolutional Networkscited by 1,488
  10. 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,436
  11. 2024Depth Anything V2cited by 1,422
  12. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  13. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
  14. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,304
  15. 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
  16. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  17. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  18. 2021EfficientNetV2: Smaller Models and Faster Trainingcited by 1,135
  19. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
  20. 2021Volume Rendering of Neural Implicit Surfacescited by 996
  21. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  22. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 968
  23. 2021Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstructioncited by 964
  24. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
  25. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  26. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 843
  27. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
  28. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
  29. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
  30. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 739
  31. 2020Implicit Geometric Regularization for Learning Shapescited by 710
  32. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 684
  33. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
  34. 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 616
  35. 2018Free-Form Image Inpainting with Gated Convolutioncited by 594
  36. 2021Ref-NeRF: Structured View-Dependent Appearance for Neural Radiance Fieldscited by 575
  37. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 566
  38. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565

50 most cited of 172 All 172 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 10; 2026: 8.

18 papers.

Sort:

  1. 2025MVSAnywhere: Zero-Shot Multi-View Stereocited by 26
  2. 2025GaSLight: Gaussian Splats for Spatially-Varying Lighting in HDRcited by 12
  3. 2025QuickSplat: Fast 3D Surface Reconstruction via Learned Gaussian Initializationcited by 11
  4. 2025Ov3R: Open-Vocabulary Semantic 3D Reconstruction from RGB Videoscited by 10
  5. 2026SparseSplat: Towards Applicable Feed-Forward 3D Gaussian Splatting with Pixel-Unaligned Predictioncited by 7
  6. 2025GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherencecited by 6
  7. 2025VAD-GS: Visibility-Aware Densification for 3D Gaussian Splatting in Dynamic Urban Scenescited by 1
  8. 2025RocSync: Millisecond-Accurate Temporal Synchronization for Heterogeneous Camera Systemscited by 1
  9. 2025PerfCam: Digital Twinning for Production Lines Using 3D Gaussian Splatting and Vision Modelscited by 0
  10. 2025UniFField: A Generalizable Unified Neural Feature Field for Visual, Semantic, and Spatial Uncertainties in Any Scenecited by 0
  11. 2025MVS-TTA: Test-Time Adaptation for Multi-View Stereo via Meta-Auxiliary Learningcited by 0
  12. 2026Urban Neural Surface Reconstruction from Constrained Sparse Aerial Imagery with 3D SAR Fusioncited by 0
6 more
  1. 2026MGP-KAD: Multimodal Geometric Priors and Kolmogorov-Arnold Decoder for Single-View 3D Reconstruction in Complex Scenescited by 0
  2. 2026PAGaS: Pixel-Aligned 1DoF Gaussian Splatting for Depth Refinementcited by 0
  3. 2026ActMVS: Active Scene Reconstruction with Monocular Multi-View Stereocited by 0
  4. 2026MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videoscited by 0
  5. 2026ZipMVS: Multi-View Stereo with Compressed Cost Volumescited by 0
  6. 2026TV-SGS: Gaussian Splatting with Geometric Information Propagation via Tensor Voting under sparse viewscited by 0