mlsanityData to 7 Oct 2026

Multi-View Stereo with Transformer

arXiv 2112.00336 ↗First posted 1 Dec 2021cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

This paper proposes a network, referred to as MVSTR, for Multi-View Stereo (MVS). It is built upon Transformer and is capable of extracting dense features with global context and 3D consistency, which are crucial to achieving reliable matching for MVS. Specifically, to tackle the problem of the limited receptive field of existing CNN-based MVS methods, a global-context Transformer module is first proposed to explore intra-view global context. In addition, to further enable dense features to be 3D-consistent, a 3D-geometry Transformer module is built with a well-designed cross-view attention mechanism to facilitate inter-view information interaction. Experimental results show that the proposed MVSTR achieves the best overall performance on the DTU dataset and strong generalization on the Tanks & Temples benchmark dataset.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 26 of its 39 references that are in the map. First posted on arXiv 1 Dec 2021.

Builds on

26 of 39 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  7. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 1,979
  8. 2020Reformer: The Efficient Transformercited by 1,658
  9. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  10. 2020Pre-Trained Image Processing Transformercited by 891
  11. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
  12. 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 414
14 more
  1. 2017End-to-End Learning of Geometry and Context for Deep Stereo Regressioncited by 359
  2. 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 252
  3. 2020PatchmatchNet: Learned Multi-View Patchmatch Stereocited by 204
  4. 2020Revisiting Stereo Depth Estimation From a Sequence-to-Sequence Perspective with Transformerscited by 190
  5. 2019Cost Volume Pyramid Based Depth Inference for Multi-View Stereocited by 154
  6. 2019Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awarenesscited by 151
  7. 2019Point-Based Multi-View Stereo Networkcited by 147
  8. 2017SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsiscited by 128
  9. 2019Multi-Scale Geometric Consistency Guided Multi-View Stereocited by 105
  10. 2020Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinementcited by 105
  11. 2017In-Place Activated BatchNorm for Memory-Optimized Training of DNNscited by 81
  12. 2021AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Networkcited by 71
  13. 2019Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volumecited by 59
  14. 2019Pyramid Multi-view Stereo Net with Self-adaptive View Aggregationcited by 44

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 5; 2024: 2; 2025: 1; 2026: 2.

14 papers.

Sort:

  1. 2022MVSTER: Epipolar Transformer for Efficient Multi-View Stereocited by 50
  2. 2022MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depthcited by 50
  3. 2023S-VolSDF: Sparse Multi-View Stereo Regularization of Neural Implicit Surfacescited by 21
  4. 2023C2F2NeUS: Cascade Cost Frustum Fusion for High Fidelity and Generalizable Neural Surface Reconstructioncited by 18
  5. 2023RayMVSNet++: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereocited by 15
  6. 2023CostFormer:Cost Transformer for Cost Aggregation in Multi-view Stereocited by 9
  7. 2022Semi-supervised Deep Multi-view Stereocited by 5
  8. 2022Rethinking Disparity: A Depth Range Free Multi-View Stereo Based on Disparitycited by 3
  9. 2024A Global Depth-Range-Free Multi-View Stereo Transformer Network with Pose Embeddingcited by 3
  10. 2025DePT3R: Joint Dense Point Tracking and 3D Reconstruction of Dynamic Scenes in a Single Forward Passcited by 3
  11. 2023Learning Deformable Hypothesis Sampling for Accurate PatchMatch Multi-View Stereocited by 1
  12. 2024Geometric Constraints in Deep Learning Frameworks: A Surveycited by 1
2 more
  1. 2026Reference-Free Omnidirectional Stereo Matching via Multi-View Consistency Maximizationcited by 0
  2. 20263DTV: A Feedforward Interpolation Network for Real-Time View Synthesiscited by 0