DORNet: A Degradation Oriented and Regularized Network for Blind Depth Super-Resolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Zhengxue, Yan, Zhiqiang, Pan, Jinshan, Gao, Guangwei, Zhang, Kai, Yang, Jian
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912281860767744
author Wang, Zhengxue
Yan, Zhiqiang
Pan, Jinshan
Gao, Guangwei
Zhang, Kai
Yang, Jian
author_facet Wang, Zhengxue
Yan, Zhiqiang
Pan, Jinshan
Gao, Guangwei
Zhang, Kai
Yang, Jian
contents Recent RGB-guided depth super-resolution methods have achieved impressive performance under the assumption of fixed and known degradation (e.g., bicubic downsampling). However, in real-world scenarios, captured depth data often suffer from unconventional and unknown degradation due to sensor limitations and complex imaging environments (e.g., low reflective surfaces, varying illumination). Consequently, the performance of these methods significantly declines when real-world degradation deviate from their assumptions. In this paper, we propose the Degradation Oriented and Regularized Network (DORNet), a novel framework designed to adaptively address unknown degradation in real-world scenes through implicit degradation representations. Our approach begins with the development of a self-supervised degradation learning strategy, which models the degradation representations of low-resolution depth data using routing selection-based degradation regularization. To facilitate effective RGB-D fusion, we further introduce a degradation-oriented feature transformation module that selectively propagates RGB content into the depth data based on the learned degradation priors. Extensive experimental results on both real and synthetic datasets demonstrate the superiority of our DORNet in handling unknown degradation, outperforming existing methods. The code is available at https://github.com/yanzq95/DORNet.
format Preprint
id arxiv_https___arxiv_org_abs_2410_11666
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DORNet: A Degradation Oriented and Regularized Network for Blind Depth Super-Resolution
Wang, Zhengxue
Yan, Zhiqiang
Pan, Jinshan
Gao, Guangwei
Zhang, Kai
Yang, Jian
Computer Vision and Pattern Recognition
Recent RGB-guided depth super-resolution methods have achieved impressive performance under the assumption of fixed and known degradation (e.g., bicubic downsampling). However, in real-world scenarios, captured depth data often suffer from unconventional and unknown degradation due to sensor limitations and complex imaging environments (e.g., low reflective surfaces, varying illumination). Consequently, the performance of these methods significantly declines when real-world degradation deviate from their assumptions. In this paper, we propose the Degradation Oriented and Regularized Network (DORNet), a novel framework designed to adaptively address unknown degradation in real-world scenes through implicit degradation representations. Our approach begins with the development of a self-supervised degradation learning strategy, which models the degradation representations of low-resolution depth data using routing selection-based degradation regularization. To facilitate effective RGB-D fusion, we further introduce a degradation-oriented feature transformation module that selectively propagates RGB content into the depth data based on the learned degradation priors. Extensive experimental results on both real and synthetic datasets demonstrate the superiority of our DORNet in handling unknown degradation, outperforming existing methods. The code is available at https://github.com/yanzq95/DORNet.
title DORNet: A Degradation Oriented and Regularized Network for Blind Depth Super-Resolution
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.11666