SelfReDepth: Self-Supervised Real-Time Depth Restoration for Consumer-Grade Sensors

TL;DR

SelfReDepth is a self-supervised deep learning method that denoises and fills holes in depth maps from consumer-grade sensors in real-time, improving depth quality for dynamic video streams in AR applications.

Contribution

It introduces a real-time, self-supervised depth restoration approach that denoises and inpaints depth maps using sequential frames and color data, compatible with various RGB-D sensors.

Findings

Achieves over 30fps performance on real-world datasets.

Outperforms existing denoising methods in accuracy.

Enhances depth map quality for AR applications.

Abstract

Depth maps produced by consumer-grade sensors suffer from inaccurate measurements and missing data from either system or scene-specific sources. Data-driven denoising algorithms can mitigate such problems. However, they require vast amounts of ground truth depth data. Recent research has tackled this limitation using self-supervised learning techniques, but it requires multiple RGB-D sensors. Moreover, most existing approaches focus on denoising single isolated depth maps or specific subjects of interest, highlighting a need for methods to effectively denoise depth maps in real-time dynamic environments. This paper extends state-of-the-art approaches for depth-denoising commodity depth devices, proposing SelfReDepth, a self-supervised deep learning technique for depth restoration, via denoising and hole-filling by inpainting full-depth maps captured with RGB-D sensors. The algorithm targets depth data in video streams, utilizing multiple sequential depth frames coupled with color data to achieve high-quality depth videos with temporal coherence. Finally, SelfReDepth is designed to be compatible with various RGB-D sensors and usable in real-time scenarios as a pre-processing step before applying other depth-dependent algorithms. Our results demonstrate our approach's real-time performance on real-world datasets. They show that it outperforms state-of-the-art denoising and restoration performance at over 30fps on Commercial Depth Cameras, with potential benefits for augmented and mixed-reality applications.