# Self-Supervised Learning of Depth and Motion Under Photometric Inconsistency

arXiv: https://arxiv.org/abs/1909.09115 · HTML: https://mlsanity.com/paper/1909.09115/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Sep 2019.

## Built on by (most cited first, 6 of 6)

- [SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation](https://mlsanity.com/paper/2204.03636/) (2022)
- [OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments](https://mlsanity.com/paper/2312.09243/) (2023)
- [Deep Matching Prior: Test-Time Optimization for Dense Correspondence](https://mlsanity.com/paper/2106.03090/) (2021)
- [Diffusion Model for Dense Matching](https://mlsanity.com/paper/2305.19094/) (2023)
- [Self-Supervised Learning of Depth and Ego-Motion from Video by Alternative Training and Geometric Constraints from 3D to 2D](https://mlsanity.com/paper/2108.01980/) (2021)
- [Ada-TransGNN: An Air Quality Prediction Model Based On Adaptive Graph Convolutional Networks](https://mlsanity.com/paper/2508.17867/) (2025)

## Abstract (arXiv)

The self-supervised learning of depth and pose from monocular sequences provides an attractive solution by using the photometric consistency of nearby frames as it depends much less on the ground-truth data. In this paper, we address the issue when previous assumptions of the self-supervised approaches are violated due to the dynamic nature of real-world scenes. Different from handling the noise as uncertainty, our key idea is to incorporate more robust geometric quantities and enforce internal consistency in the temporal image sequence. As demonstrated on commonly used benchmark datasets, the proposed method substantially improves the state-of-the-art methods on both depth and relative pose estimation for monocular image sequences, without adding inference overhead.