mlsanityData to 7 Oct 2026

GC-MVSNet: Multi-View, Multi-Scale, Geometrically-Consistent Multi-View Stereo

arXiv 2310.19583 ↗First posted 30 Oct 2023cs.CV cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Traditional multi-view stereo (MVS) methods rely heavily on photometric and geometric consistency constraints, but newer machine learning-based MVS methods check geometric consistency across multiple source views only as a post-processing step. In this paper, we present a novel approach that explicitly encourages geometric consistency of reference view depth maps across multiple source views at different scales during learning (see Fig. 1). We find that adding this geometric consistency loss significantly accelerates learning by explicitly penalizing geometrically inconsistent pixels, reducing the training iteration requirements to nearly half that of other MVS methods. Our extensive experiments show that our approach achieves a new state-of-the-art on the DTU and BlendedMVS datasets, and competitive results on the Tanks and Temples benchmark. To the best of our knowledge, GC-MVSNet is the first attempt to enforce multi-view, multi-scale geometric consistency during learning.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 32 of its 56 references that are in the map. First posted on arXiv 30 Oct 2023.

Builds on

32 of 56 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 1,979
  7. 2018Group Normalizationcited by 1,514
  8. 2017Deformable Convolutional Networkscited by 1,481
  9. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  10. 2018Deformable ConvNets v2: More Deformable, Better Resultscited by 666
  11. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 487
  12. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 414
20 more
  1. 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 252
  2. 2019Cost Volume Pyramid Based Depth Inference for Multi-View Stereocited by 154
  3. 2019Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awarenesscited by 151
  4. 2019Point-Based Multi-View Stereo Networkcited by 147
  5. 2017SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsiscited by 128
  6. 2021TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformerscited by 117
  7. 2019Multi-Scale Geometric Consistency Guided Multi-View Stereocited by 105
  8. 2020Visibility-aware Multi-view Stereo Networkcited by 97
  9. 2018Hierarchical Discrete Distribution Decomposition for Match Density Estimationcited by 93
  10. 2022Rethinking Depth Estimation for Multi-View Stereo: A Unified Representationcited by 82
  11. 2020Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checkingcited by 81
  12. 2018Real-time self-adaptive deep stereocited by 80
  13. 2021AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Networkcited by 71
  14. 2018Anytime Stereo Image Depth Estimation on Mobile Devicescited by 54
  15. 2019Micro-Batch Training with Batch-Channel Normalization and Weight Standardizationcited by 45
  16. 2021Generalized Binary Search Network for Highly-Efficient Multi-View Stereocited by 32
  17. 2021Curvature-guided dynamic scale networks for Multi-view Stereocited by 17
  18. 2020Attention Aware Cost Volume Pyramid Based Multi-view Stereo Network for 3D Reconstructioncited by 13
  19. 2021Deep Multi-View Stereo gone wildcited by 11
  20. 2021Non-local Recurrent Regularization Networks for Multi-view Stereocited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 3; 2026: 2.

8 papers.

  1. 2024INPC: Implicit Neural Point Clouds for Radiance Field Renderingcited by 10
  2. 2026STAC: Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstructioncited by 8
  3. 2025Lightweight and Accurate Multi-View Stereo with Confidence-Aware Diffusion Modelcited by 4
  4. 2024SDL-MVS: View Space and Depth Deformable Learning Paradigm for Multi-View Stereo Reconstruction in Remote Sensingcited by 3
  5. 2024Geometric Constraints in Deep Learning Frameworks: A Surveycited by 1
  6. 2025Blending 3D Geometry and Machine Learning for Multi-View Stereopsiscited by 0
  7. 2025IA-MVS: Instance-Focused Adaptive Depth Sampling for Multi-View Stereocited by 0
  8. 2026Lite3R: A Model-Agnostic Framework for Efficient Feed-Forward 3D Reconstructioncited by 0