# Stereo-Matching Knowledge Distilled Monocular Depth Estimation Filtered by Multiple Disparity Consistency

arXiv: https://arxiv.org/abs/2401.12019 · HTML: https://mlsanity.com/paper/2401.12019/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 22 references that are in the map.
- First posted on arXiv 22 Jan 2024.

## Builds on (most cited first, 14 of 14)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Depth Map Prediction from a Single Image using a Multi-Scale Deep Network](https://mlsanity.com/paper/1406.2283/) (2014)
- [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016)
- [Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue](https://mlsanity.com/paper/1603.04992/) (2016)
- [On the uncertainty of self-supervised monocular depth estimation](https://mlsanity.com/paper/2005.06209/) (2020)
- [Self-Supervised Monocular Depth Hints](https://mlsanity.com/paper/1909.09051/) (2019)
- [Learning Monocular Depth by Distilling Cross-domain Stereo Networks](https://mlsanity.com/paper/1808.06586/) (2018)
- [Learning monocular depth estimation infusing traditional stereo knowledge](https://mlsanity.com/paper/1904.04144/) (2019)
- [Learning Stereo from Single Images](https://mlsanity.com/paper/2008.01484/) (2020)
- [Learning to Adapt for Stereo](https://mlsanity.com/paper/1904.02957/) (2019)
- [Unsupervised Domain Adaptation for Depth Prediction from Images](https://mlsanity.com/paper/1909.03943/) (2019)
- [Adaptive confidence thresholding for monocular depth estimation](https://mlsanity.com/paper/2009.12840/) (2020)

## Abstract (arXiv)

In stereo-matching knowledge distillation methods of the self-supervised monocular depth estimation, the stereo-matching network's knowledge is distilled into a monocular depth network through pseudo-depth maps. In these methods, the learning-based stereo-confidence network is generally utilized to identify errors in the pseudo-depth maps to prevent transferring the errors. However, the learning-based stereo-confidence networks should be trained with ground truth (GT), which is not feasible in a self-supervised setting. In this paper, we propose a method to identify and filter errors in the pseudo-depth map using multiple disparity maps by checking their consistency without the need for GT and a training process. Experimental results show that the proposed method outperforms the previous methods and works well on various configurations by filtering out erroneous areas where the stereo-matching is vulnerable, especially such as textureless regions, occlusion boundaries, and reflective surfaces.