# Deep PatchMatch MVS with Learned Patch Coplanarity, Geometric Consistency and Adaptive Pixel Sampling

arXiv: https://arxiv.org/abs/2210.07582 · HTML: https://mlsanity.com/paper/2210.07582/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 36 references that are in the map.
- First posted on arXiv 14 Oct 2022.

## Builds on (most cited first, 13 of 13)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [MVSNet: Depth Inference for Unstructured Multi-view Stereo](https://mlsanity.com/paper/1804.02505/) (2018)
- [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)
- [Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inference](https://mlsanity.com/paper/1902.10556/) (2019)
- [PatchmatchNet: Learned Multi-View Patchmatch Stereo](https://mlsanity.com/paper/2012.01411/) (2020)
- [Learning Depth with Convolutional Spatial Propagation Network](https://mlsanity.com/paper/1810.02695/) (2018)
- [Multi-Scale Geometric Consistency Guided Multi-View Stereo](https://mlsanity.com/paper/1904.08103/) (2019)
- [Visibility-aware Multi-view Stereo Network](https://mlsanity.com/paper/2008.07928/) (2020)
- [Planar Prior Assisted PatchMatch Multi-View Stereo](https://mlsanity.com/paper/1912.11744/) (2019)
- [TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo](https://mlsanity.com/paper/1903.10929/) (2019)
- [PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibility](https://mlsanity.com/paper/2108.08943/) (2021)

## Built on by (most cited first, 1 of 1)

- [Learning Deformable Hypothesis Sampling for Accurate PatchMatch Multi-View Stereo](https://mlsanity.com/paper/2312.15970/) (2023)

## Abstract (arXiv)

Recent work in multi-view stereo (MVS) combines learnable photometric scores and regularization with PatchMatch-based optimization to achieve robust pixelwise estimates of depth, normals, and visibility. However, non-learning based methods still outperform for large scenes with sparse views, in part due to use of geometric consistency constraints and ability to optimize over many views at high resolution. In this paper, we build on learning-based approaches to improve photometric scores by learning patch coplanarity and encourage geometric consistency by learning a scaled photometric cost that can be combined with reprojection error. We also propose an adaptive pixel sampling strategy for candidate propagation that reduces memory to enable training on larger resolution with more views and a larger encoder. These modifications lead to 6-15% gains in accuracy and completeness on the challenging ETH3D benchmark, resulting in higher F1 performance than the widely used state-of-the-art non-learning approaches ACMM and ACMP.