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

TL;DR

DORNet is a novel depth super-resolution framework that adaptively models unknown real-world degradation using self-supervised learning and degradation priors, significantly improving performance over existing methods.

Contribution

The paper introduces a self-supervised degradation learning strategy and a degradation-oriented feature transformation module for blind depth super-resolution.

Findings

Outperforms existing methods on real and synthetic datasets.

Effectively models unknown degradation in real-world scenes.

Enhances RGB-D fusion by leveraging learned degradation priors.

Abstract

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.