Unsupervised Monocular Depth Learning in Dynamic Scenes

Hanhan Li, Ariel Gordon, Hang Zhao, Vincent Casser, Anelia Angelova
10/30/2020
cs.CVcs.GRcs.LG

Official code: google-research/google-research (39,000 stars, Apache-2.0, last commit 2026-04-30).

Abstract

We present a method for jointly training the estimation of depth, ego-motion, and a dense 3D translation field of objects relative to the scene, with monocular photometric consistency being the sole source of supervision. We show that this apparently heavily underdetermined problem can be regularized by imposing the following prior knowledge about 3D translation fields: they are sparse, since most of the scene is static, and they tend to be constant for rigid moving objects. We show that this regularization alone is sufficient to train monocular depth prediction models that exceed the accuracy achieved in prior work for dynamic scenes, including methods that require semantic input. Code is at https://github.com/google-research/google-research/tree/master/depth_and_motion_learning .

View on arXivView PDF

Code Implementations(1)

google-research/google-researchOfficial100%
Apache-2.0

Google Research

39,0008,488C, ROct 4, 20185 months agoApache-2.0
aimachine-learningresearch

Similar Papers

From-Ground-To-Objects: Coarse-to-Fine Self-supervised Monocular Depth Estimation of Dynamic Objects with Ground Contact Prior

89% match2023

Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimation

89% match1 repo142024

RM-Depth: Unsupervised Learning of Recurrent Monocular Depth in Dynamic Scenes

89% match1 repo412023

Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes

88% match1 repo892023

UM-Depth : Uncertainty Masked Self-Supervised Monocular Depth Estimation with Visual Odometry

88% match2025

Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints

88% match1 repo77.7k2018

Cite this paper

@article{li2020unsupervised,
  title  = {Unsupervised Monocular Depth Learning in Dynamic Scenes},
  author = {Hanhan Li and Ariel Gordon and Hang Zhao and Vincent Casser and Anelia Angelova},
  year   = {2020},
  eprint = {2010.16404},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2010.16404}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2010.16404.svg)](https://codeofpaper.com/paper/2010.16404)

Discussion