Unsupervised Monocular Depth and Ego-motion Learning with Structure and Semantics

06/12/2019
by   Vincent Casser, et al.
6

We present an approach which takes advantage of both structure and semantics for unsupervised monocular learning of depth and ego-motion. More specifically, we model the motion of individual objects and learn their 3D motion vector jointly with depth and ego-motion. We obtain more accurate results, especially for challenging dynamic scenes not addressed by previous approaches. This is an extended version of Casser et al. [AAAI'19]. Code and models have been open sourced at https://sites.google.com/corp/view/struct2depth.

READ FULL TEXT

page 2

page 4

page 5

page 6

page 7

research
10/30/2020

Unsupervised Monocular Depth Learning in Dynamic Scenes

We present a method for jointly training the estimation of depth, ego-mo...
research
11/15/2018

Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos

Learning to predict scene depth from RGB inputs is a challenging task bo...
research
06/08/2020

Semantics-Driven Unsupervised Learning for Monocular Depth and Ego-Motion Estimation

We propose a semantics-driven unsupervised learning approach for monocul...
research
12/31/2020

Unsupervised Monocular Depth Reconstruction of Non-Rigid Scenes

Monocular depth reconstruction of complex and dynamic scenes is a highly...
research
03/08/2023

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

Unsupervised methods have showed promising results on monocular depth es...
research
03/03/2020

DiPE: Deeper into Photometric Errors for Unsupervised Learning of Depth and Ego-motion from Monocular Videos

Unsupervised learning of depth and ego-motion from unlabelled monocular ...
research
02/04/2021

Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency

We present an end-to-end joint training framework that explicitly models...

Please sign up or login with your details

Forgot password? Click here to reset