Self-supervised Depth Denoising Using Lower- and Higher-quality RGB-D sensors

09/10/2020
by   Akhmedkhan Shabanov, et al.
7

Consumer-level depth cameras and depth sensors embedded in mobile devices enable numerous applications, such as AR games and face identification. However, the quality of the captured depth is sometimes insufficient for 3D reconstruction, tracking and other computer vision tasks. In this paper, we propose a self-supervised depth denoising approach to denoise and refine depth coming from a low quality sensor. We record simultaneous RGB-D sequences with unzynchronized lower- and higher-quality cameras and solve a challenging problem of aligning sequences both temporally and spatially. We then learn a deep neural network to denoise the lower-quality depth using the matched higher-quality data as a source of supervision signal. We experimentally validate our method against state-of-the-art filtering-based and deep denoising techniques and show its application for 3D object reconstruction tasks where our approach leads to more detailed fused surfaces and better tracking.

READ FULL TEXT

page 1

page 6

page 8

page 10

page 11

research
05/09/2023

Multi-Object Self-Supervised Depth Denoising

Depth cameras are frequently used in robotic manipulation, e.g. for visu...
research
09/03/2019

Self-Supervised Deep Depth Denoising

Depth perception is considered an invaluable source of information for v...
research
02/12/2019

Towards Self-Supervised High Level Sensor Fusion

In this paper, we present a framework to control a self-driving car by f...
research
12/05/2022

SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields

3D reconstruction from 2D image was extensively studied, training with d...
research
05/10/2022

Self-supervised regression learning using domain knowledge: Applications to improving self-supervised denoising in imaging

Regression that predicts continuous quantity is a central part of applic...
research
06/16/2020

Depth by Poking: Learning to Estimate Depth from Self-Supervised Grasping

Accurate depth estimation remains an open problem for robotic manipulati...
research
12/13/2015

A Person Re-Identification System For Mobile Devices

Person re-identification is a critical security task for recognizing a p...

Please sign up or login with your details

Forgot password? Click here to reset