# Fusion of stereo and still monocular depth estimates in a self-supervised learning context

arXiv: https://arxiv.org/abs/1803.07512 · HTML: https://mlsanity.com/paper/1803.07512/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Mar 2018.

## Built on by (most cited first, 10 of 10)

- [The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth](https://mlsanity.com/paper/2104.14540/) (2021)
- [UncLe-SLAM: Uncertainty Learning for Dense Neural SLAM](https://mlsanity.com/paper/2306.11048/) (2023)
- [Diving into the Fusion of Monocular Priors for Generalized Stereo Matching](https://mlsanity.com/paper/2505.14414/) (2025)
- [Two-in-One Depth: Bridging the Gap Between Monocular and Binocular Self-supervised Depth Estimation](https://mlsanity.com/paper/2309.00933/) (2023)
- [Learning Online Multi-Sensor Depth Fusion](https://mlsanity.com/paper/2204.03353/) (2022)
- [Self-Supervised Monocular Depth Estimation of Untextured Indoor Rotated Scenes](https://mlsanity.com/paper/2106.12958/) (2021)
- [Panoramic Depth Estimation via Supervised and Unsupervised Learning in Indoor Scenes](https://mlsanity.com/paper/2108.08076/) (2021)
- [Learning Monocular Depth Estimation via Selective Distillation of Stereo Knowledge](https://mlsanity.com/paper/2205.08668/) (2022)
- [Deep Learning-based High-precision Depth Map Estimation from Missing Viewpoints for 360 Degree Digital Holography](https://mlsanity.com/paper/2103.05158/) (2021)
- [Multi-Scale Cost Volumes Cascade Network for Stereo Matching](https://mlsanity.com/paper/2102.01940/) (2021)

## Abstract (arXiv)

We study how autonomous robots can learn by themselves to improve their depth estimation capability. In particular, we investigate a self-supervised learning setup in which stereo vision depth estimates serve as targets for a convolutional neural network (CNN) that transforms a single still image to a dense depth map. After training, the stereo and mono estimates are fused with a novel fusion method that preserves high confidence stereo estimates, while leveraging the CNN estimates in the low-confidence regions. The main contribution of the article is that it is shown that the fused estimates lead to a higher performance than the stereo vision estimates alone. Experiments are performed on the KITTI dataset, and on board of a Parrot SLAMDunk, showing that even rather limited CNNs can help provide stereo vision equipped robots with more reliable depth maps for autonomous navigation.