# DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction

arXiv: https://arxiv.org/abs/1912.00439 · HTML: https://mlsanity.com/paper/1912.00439/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2019.

## Built on by (most cited first, 23 of 23)

- [TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers](https://mlsanity.com/paper/2111.14600/) (2021)
- [Learning Signed Distance Field for Multi-view Surface Reconstruction](https://mlsanity.com/paper/2108.09964/) (2021)
- [AA-RMVSNet: Adaptive Aggregation Recurrent Multi-view Stereo Network](https://mlsanity.com/paper/2108.03824/) (2021)
- [IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo](https://mlsanity.com/paper/2112.05126/) (2021)
- [Multiview Stereo with Cascaded Epipolar RAFT](https://mlsanity.com/paper/2205.04502/) (2022)
- [Digging into Uncertainty in Self-supervised Multi-view Stereo](https://mlsanity.com/paper/2108.12966/) (2021)
- [Robust Incremental Structure-from-Motion with Hybrid Features](https://mlsanity.com/paper/2409.19811/) (2024)
- [UncLe-SLAM: Uncertainty Learning for Dense Neural SLAM](https://mlsanity.com/paper/2306.11048/) (2023)
- [Learning-based Multi-View Stereo: A Survey](https://mlsanity.com/paper/2408.15235/) (2024)
- [PatchMatch-RL: Deep MVS with Pixelwise Depth, Normal, and Visibility](https://mlsanity.com/paper/2108.08943/) (2021)
- [Multi-sensor large-scale dataset for multi-view 3D reconstruction](https://mlsanity.com/paper/2203.06111/) (2022)
- [A Confidence-based Iterative Solver of Depths and Surface Normals for Deep Multi-view Stereo](https://mlsanity.com/paper/2201.07609/) (2022)
- [TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo](https://mlsanity.com/paper/2308.09990/) (2023)
- [NeuralRoom: Geometry-Constrained Neural Implicit Surfaces for Indoor Scene Reconstruction](https://mlsanity.com/paper/2210.06853/) (2022)
- [IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions](https://mlsanity.com/paper/2111.14420/) (2021)
- [Enhancing Multi-view Stereo with Contrastive Matching and Weighted Focal Loss](https://mlsanity.com/paper/2206.10360/) (2022)
- [CHOSEN: Contrastive Hypothesis Selection for Multi-View Depth Refinement](https://mlsanity.com/paper/2404.02225/) (2024)
- [SceneDiff: A Benchmark and Method for Multiview Object Change Detection](https://mlsanity.com/paper/2512.16908/) (2025)
- [Revisiting PatchMatch Multi-View Stereo for Urban 3D Reconstruction](https://mlsanity.com/paper/2207.08439/) (2022)
- [DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo](https://mlsanity.com/paper/2212.06626/) (2022)
- [MonoPatchNeRF: Improving Neural Radiance Fields with Patch-based Monocular Guidance](https://mlsanity.com/paper/2404.08252/) (2024)
- [Image Stabilization for Hololens Camera in Remote Collaboration](https://mlsanity.com/paper/2304.02736/) (2023)
- [MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo](https://mlsanity.com/paper/2309.13294/) (2023)

## Abstract (arXiv)

Deep Neural Networks (DNNs) have the potential to improve the quality of image-based 3D reconstructions. However, the use of DNNs in the context of 3D reconstruction from large and high-resolution image datasets is still an open challenge, due to memory and computational constraints. We propose a pipeline which takes advantage of DNNs to improve the quality of 3D reconstructions while being able to handle large and high-resolution datasets. In particular, we propose a confidence prediction network explicitly tailored for Multi-View Stereo (MVS) and we use it for both depth map outlier filtering and depth map refinement within our pipeline, in order to improve the quality of the final 3D reconstructions. We train our confidence prediction network on (semi-)dense ground truth depth maps from publicly available real world MVS datasets. With extensive experiments on popular benchmarks, we show that our overall pipeline can produce state-of-the-art 3D reconstructions, both qualitatively and quantitatively.