# MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions

arXiv: https://arxiv.org/abs/2104.13325 · HTML: https://mlsanity.com/paper/2104.13325/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 61 references that are in the map.
- First posted on arXiv 27 Apr 2021.

## Builds on (most cited first, 30 of 39)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?](https://mlsanity.com/paper/1703.04977/) (2017)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (2017)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [Stand-Alone Self-Attention in Vision Models](https://mlsanity.com/paper/1906.05909/) (2019)
- [BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks](https://mlsanity.com/paper/1911.10127/) (2019)
- [Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching](https://mlsanity.com/paper/1912.06378/) (2019)
- [From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation](https://mlsanity.com/paper/1907.10326/) (2019)
- [DeepMVS: Learning Multi-view Stereopsis](https://mlsanity.com/paper/1804.00650/) (2018)
- [Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference](https://mlsanity.com/paper/1902.10556/) (2019)
- [Enforcing geometric constraints of virtual normal for depth prediction](https://mlsanity.com/paper/1907.12209/) (2019)
- [PatchmatchNet: Learned Multi-View Patchmatch Stereo](https://mlsanity.com/paper/2012.01411/) (2020)
- [Atlas: End-to-End 3D Scene Reconstruction from Posed Images](https://mlsanity.com/paper/2003.10432/) (2020)
- [AANet: Adaptive Aggregation Network for Efficient Stereo Matching](https://mlsanity.com/paper/2004.09548/) (2020)
- [DeMoN: Depth and Motion Network for Learning Monocular Stereo](https://mlsanity.com/paper/1612.02401/) (2016)
- [Learning a Multi-View Stereo Machine](https://mlsanity.com/paper/1708.05375/) (2017)
- [Cost Volume Pyramid Based Depth Inference for Multi-View Stereo](https://mlsanity.com/paper/1912.08329/) (2019)
- [Deep Stereo using Adaptive Thin Volume Representation with Uncertainty Awareness](https://mlsanity.com/paper/1911.12012/) (2019)
- [Point-Based Multi-View Stereo Network](https://mlsanity.com/paper/1908.04422/) (2019)
- [SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis](https://mlsanity.com/paper/1708.01749/) (2017)
- [HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching](https://mlsanity.com/paper/2007.12140/) (2020)
- [DPSNet: End-to-end Deep Plane Sweep Stereo](https://mlsanity.com/paper/1905.00538/) (2019)
- [DeepPruner: Learning Efficient Stereo Matching via Differentiable PatchMatch](https://mlsanity.com/paper/1909.05845/) (2019)
- [Fast-MVSNet: Sparse-to-Dense Multi-View Stereo With Learned Propagation and Gauss-Newton Refinement](https://mlsanity.com/paper/2003.13017/) (2020)
- [Computing the Stereo Matching Cost with a Convolutional Neural Network](https://mlsanity.com/paper/1409.4326/) (2014)

## Built on by (most cited first, 30 of 43)

- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [DepthSplat: Connecting Gaussian Splatting and Depth](https://mlsanity.com/paper/2410.13862/) (2024)
- [Iterative Geometry Encoding Volume for Stereo Matching](https://mlsanity.com/paper/2303.06615/) (2023)
- [Is Attention All That NeRF Needs?](https://mlsanity.com/paper/2207.13298/) (2022)
- [Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors](https://mlsanity.com/paper/2503.17316/) (2025)
- [World-consistent Video Diffusion with Explicit 3D Modeling](https://mlsanity.com/paper/2412.01821/) (2024)
- [MVSFormer: Multi-View Stereo by Learning Robust Image Features and Temperature-based Depth](https://mlsanity.com/paper/2208.02541/) (2022)
- [MVSTER: Epipolar Transformer for Efficient Multi-View Stereo](https://mlsanity.com/paper/2204.07346/) (2022)
- [Matrix3D: Large Photogrammetry Model All-in-One](https://mlsanity.com/paper/2502.07685/) (2025)
- [A Benchmark and a Baseline for Robust Multi-view Depth Estimation](https://mlsanity.com/paper/2209.06681/) (2022)
- [VoRTX: Volumetric 3D Reconstruction With Transformers for Voxelwise View Selection and Fusion](https://mlsanity.com/paper/2112.00236/) (2021)
- [Generalized Binary Search Network for Highly-Efficient Multi-View Stereo](https://mlsanity.com/paper/2112.02338/) (2021)
- [Input-level Inductive Biases for 3D Reconstruction](https://mlsanity.com/paper/2112.03243/) (2021)
- [Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving](https://mlsanity.com/paper/2403.07535/) (2024)
- [Cross-View Completion Models are Zero-shot Correspondence Estimators](https://mlsanity.com/paper/2412.09072/) (2024)
- [MVSAnywhere: Zero-Shot Multi-View Stereo](https://mlsanity.com/paper/2503.22430/) (2025)
- [Learning to Fuse Monocular and Multi-view Cues for Multi-frame Depth Estimation in Dynamic Scenes](https://mlsanity.com/paper/2304.08993/) (2023)
- [3DVNet: Multi-View Depth Prediction and Volumetric Refinement](https://mlsanity.com/paper/2112.00202/) (2021)
- [WT-MVSNet: Window-based Transformers for Multi-view Stereo](https://mlsanity.com/paper/2205.14319/) (2022)
- [Multi-view Reconstruction via SfM-guided Monocular Depth Estimation](https://mlsanity.com/paper/2503.14483/) (2025)
- [Test3R: Learning to Reconstruct 3D at Test Time](https://mlsanity.com/paper/2506.13750/) (2025)
- [MonSter++: Unified Stereo Matching, Multi-view Stereo, and Real-time Stereo with Monodepth Priors](https://mlsanity.com/paper/2501.08643/) (2025)
- [RayMVSNet++: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereo](https://mlsanity.com/paper/2307.10233/) (2023)
- [Free-Editor: Zero-shot Text-driven 3D Scene Editing](https://mlsanity.com/paper/2312.13663/) (2023)
- [PE3R: Perception-Efficient 3D Reconstruction](https://mlsanity.com/paper/2503.07507/) (2025)
- [Joint Depth Prediction and Semantic Segmentation with Multi-View SAM](https://mlsanity.com/paper/2311.00134/) (2023)
- [Direct and Explicit 3D Generation from a Single Image](https://mlsanity.com/paper/2411.10947/) (2024)
- [Pixel-Aligned Multi-View Generation with Depth Guided Decoder](https://mlsanity.com/paper/2408.14016/) (2024)
- [Multi-view Gaze Target Estimation](https://mlsanity.com/paper/2508.05857/) (2025)
- [Rethinking Disparity: A Depth Range Free Multi-View Stereo Based on Disparity](https://mlsanity.com/paper/2211.16905/) (2022)

## Abstract (arXiv)

Deep learning has made significant impacts on multi-view stereo systems. State-of-the-art approaches typically involve building a cost volume, followed by multiple 3D convolution operations to recover the input image's pixel-wise depth. While such end-to-end learning of plane-sweeping stereo advances public benchmarks' accuracy, they are typically very slow to compute. We present ouralg, a highly efficient multi-view stereo algorithm that seamlessly integrates multi-view constraints into single-view networks via an attention mechanism. Since ouralg only builds on 2D convolutions, it is at least 2× faster than all the notable counterparts. Moreover, our algorithm produces precise depth estimations and 3D reconstructions, achieving state-of-the-art results on challenging benchmarks ScanNet, SUN3D, RGBD, and the classical DTU dataset. our algorithm also out-performs all other algorithms in the setting of inexact camera poses. Our code is released at urlhttps://github.com/zhenpeiyang/MVS2D