# Learning Unsupervised Multi-View Stereopsis via Robust Photometric Consistency

arXiv: https://arxiv.org/abs/1905.02706 · HTML: https://mlsanity.com/paper/1905.02706/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2019.

## Built on by (most cited first, 30 of 40)

- [Neural Fields in Visual Computing and Beyond](https://mlsanity.com/paper/2111.11426/) (2021)
- [The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth](https://mlsanity.com/paper/2104.14540/) (2021)
- [GeCoNeRF: Few-shot Neural Radiance Fields via Geometric Consistency](https://mlsanity.com/paper/2301.10941/) (2023)
- [Full Surround Monodepth from Multiple Cameras](https://mlsanity.com/paper/2104.00152/) (2021)
- [Self-supervised Multi-view Stereo via Effective Co-Segmentation and Data-Augmentation](https://mlsanity.com/paper/2104.05374/) (2021)
- [Digging into Uncertainty in Self-supervised Multi-view Stereo](https://mlsanity.com/paper/2108.12966/) (2021)
- [RC-MVSNet: Unsupervised Multi-View Stereo with Neural Rendering](https://mlsanity.com/paper/2203.03949/) (2022)
- [Self-supervised Learning of Depth Inference for Multi-view Stereo](https://mlsanity.com/paper/2104.02972/) (2021)
- [MVSAnywhere: Zero-Shot Multi-View Stereo](https://mlsanity.com/paper/2503.22430/) (2025)
- [Sparse2DGS: Geometry-Prioritized Gaussian Splatting for Surface Reconstruction from Sparse Views](https://mlsanity.com/paper/2504.20378/) (2025)
- [KD-MVS: Knowledge Distillation Based Self-supervised Learning for Multi-view Stereo](https://mlsanity.com/paper/2207.10425/) (2022)
- [Learning-based Multi-View Stereo: A Survey](https://mlsanity.com/paper/2408.15235/) (2024)
- [Multi-Camera Collaborative Depth Prediction via Consistent Structure Estimation](https://mlsanity.com/paper/2210.02009/) (2022)
- [Prior-Guided Multi-View 3D Head Reconstruction](https://mlsanity.com/paper/2107.04277/) (2021)
- [Deep Multi-View Stereo gone wild](https://mlsanity.com/paper/2104.15119/) (2021)
- [DS-MVSNet: Unsupervised Multi-view Stereo via Depth Synthesis](https://mlsanity.com/paper/2208.06674/) (2022)
- [Geometry-aware Reconstruction and Fusion-refined Rendering for Generalizable Neural Radiance Fields](https://mlsanity.com/paper/2404.17528/) (2024)
- [DurLAR: A High-fidelity 128-channel LiDAR Dataset with Panoramic Ambient and Reflectivity Imagery for Multi-modal Autonomous Driving Applications](https://mlsanity.com/paper/2406.10068/) (2024)
- [Multi-tiling Neural Radiance Field (NeRF) -- Geometric Assessment on Large-scale Aerial Datasets](https://mlsanity.com/paper/2310.00530/) (2023)
- [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)
- [Sparse 3D Reconstruction via Object-Centric Ray Sampling](https://mlsanity.com/paper/2309.03008/) (2023)
- [CL-MVSNet: Unsupervised Multi-view Stereo with Dual-level Contrastive Learning](https://mlsanity.com/paper/2503.08219/) (2025)
- [PatchMVSNet: Patch-wise Unsupervised Multi-View Stereo for Weakly-Textured Surface Reconstruction](https://mlsanity.com/paper/2203.02156/) (2022)
- [Rethinking Disparity: A Depth Range Free Multi-View Stereo Based on Disparity](https://mlsanity.com/paper/2211.16905/) (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)
- [Improving Neural Surface Reconstruction with Feature Priors from Multi-View Image](https://mlsanity.com/paper/2408.02079/) (2024)
- [HR-NeuS: Recovering High-Frequency Surface Geometry via Neural Implicit Surfaces](https://mlsanity.com/paper/2302.06793/) (2023)
- [Improved Neural Radiance Fields Using Pseudo-depth and Fusion](https://mlsanity.com/paper/2308.03772/) (2023)
- [ViM-Disparity: Bridging the Gap of Speed, Accuracy and Memory for Disparity Map Generation](https://mlsanity.com/paper/2412.16745/) (2024)

## Abstract (arXiv)

We present a learning based approach for multi-view stereopsis (MVS). While current deep MVS methods achieve impressive results, they crucially rely on ground-truth 3D training data, and acquisition of such precise 3D geometry for supervision is a major hurdle. Our framework instead leverages photometric consistency between multiple views as supervisory signal for learning depth prediction in a wide baseline MVS setup. However, naively applying photo consistency constraints is undesirable due to occlusion and lighting changes across views. To overcome this, we propose a robust loss formulation that: a) enforces first order consistency and b) for each point, selectively enforces consistency with some views, thus implicitly handling occlusions. We demonstrate our ability to learn MVS without 3D supervision using a real dataset, and show that each component of our proposed robust loss results in a significant improvement. We qualitatively observe that our reconstructions are often more complete than the acquired ground truth, further showing the merits of this approach. Lastly, our learned model generalizes to novel settings, and our approach allows adaptation of existing CNNs to datasets without ground-truth 3D by unsupervised finetuning. Project webpage: https://tejaskhot.github.io/unsup_mvs