# Deep Multi-view Depth Estimation with Predicted Uncertainty

arXiv: https://arxiv.org/abs/2011.09594 · HTML: https://mlsanity.com/paper/2011.09594/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2020.

## Built on by (most cited first, 11 of 11)

- [Unifying Flow, Stereo and Depth Estimation](https://mlsanity.com/paper/2211.05783/) (2022)
- [Multi-Frame Self-Supervised Depth with Transformers](https://mlsanity.com/paper/2204.07616/) (2022)
- [Learning Optical Flow, Depth, and Scene Flow without Real-World Labels](https://mlsanity.com/paper/2203.15089/) (2022)
- [Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion](https://mlsanity.com/paper/2501.18804/) (2025)
- [Self-supervised Remote Sensing Images Change Detection at Pixel-level](https://mlsanity.com/paper/2105.08501/) (2021)
- [Dense Uncertainty Estimation](https://mlsanity.com/paper/2110.06427/) (2021)
- [DS-Depth: Dynamic and Static Depth Estimation via a Fusion Cost Volume](https://mlsanity.com/paper/2308.07225/) (2023)
- [Exploiting Correspondences with All-pairs Correlations for Multi-view Depth Estimation](https://mlsanity.com/paper/2205.02481/) (2022)
- [Learning Implicit Functions for Dense 3D Shape Correspondence of Generic Objects](https://mlsanity.com/paper/2212.14276/) (2022)
- [Bayesian Approximation-Based Trajectory Prediction and Tracking with 4D Radar](https://mlsanity.com/paper/2502.01357/) (2025)
- [A technique to jointly estimate depth and depth uncertainty for unmanned aerial vehicles](https://mlsanity.com/paper/2305.19780/) (2023)

## Abstract (arXiv)

In this paper, we address the problem of estimating dense depth from a sequence of images using deep neural networks. Specifically, we employ a dense-optical-flow network to compute correspondences and then triangulate the point cloud to obtain an initial depth map.Parts of the point cloud, however, may be less accurate than others due to lack of common observations or small parallax. To further increase the triangulation accuracy, we introduce a depth-refinement network (DRN) that optimizes the initial depth map based on the image's contextual cues. In particular, the DRN contains an iterative refinement module (IRM) that improves the depth accuracy over iterations by refining the deep features. Lastly, the DRN also predicts the uncertainty in the refined depths, which is desirable in applications such as measurement selection for scene reconstruction. We show experimentally that our algorithm outperforms state-of-the-art approaches in terms of depth accuracy, and verify that our predicted uncertainty is highly correlated to the actual depth error.