# Learning to Adapt Multi-View Stereo by Self-Supervision

arXiv: https://arxiv.org/abs/2009.13278 · HTML: https://mlsanity.com/paper/2009.13278/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Sep 2020.

## Built on by (most cited first, 7 of 7)

- [Digging into Uncertainty in Self-supervised Multi-view Stereo](https://mlsanity.com/paper/2108.12966/) (2021)
- [Self-supervised Learning of Depth Inference for Multi-view Stereo](https://mlsanity.com/paper/2104.02972/) (2021)
- [Semi-supervised Deep Multi-view Stereo](https://mlsanity.com/paper/2207.11699/) (2022)
- [RobustMVS: Single Domain Generalized Deep Multi-view Stereo](https://mlsanity.com/paper/2405.09131/) (2024)
- [PatchMVSNet: Patch-wise Unsupervised Multi-View Stereo for Weakly-Textured Surface Reconstruction](https://mlsanity.com/paper/2203.02156/) (2022)
- [SDL-MVS: View Space and Depth Deformable Learning Paradigm for Multi-View Stereo Reconstruction in Remote Sensing](https://mlsanity.com/paper/2405.17140/) (2024)
- [Geometric Constraints in Deep Learning Frameworks: A Survey](https://mlsanity.com/paper/2403.12431/) (2024)

## Abstract (arXiv)

3D scene reconstruction from multiple views is an important classical problem in computer vision. Deep learning based approaches have recently demonstrated impressive reconstruction results. When training such models, self-supervised methods are favourable since they do not rely on ground truth data which would be needed for supervised training and is often difficult to obtain. Moreover, learned multi-view stereo reconstruction is prone to environment changes and should robustly generalise to different domains. We propose an adaptive learning approach for multi-view stereo which trains a deep neural network for improved adaptability to new target domains. We use model-agnostic meta-learning (MAML) to train base parameters which, in turn, are adapted for multi-view stereo on new domains through self-supervised training. Our evaluations demonstrate that the proposed adaptation method is effective in learning self-supervised multi-view stereo reconstruction in new domains.