Fast Color-guided Depth Denoising for RGB-D Images by Graph Filtering

TL;DR

This paper introduces a fast, color-guided graph filtering method for denoising depth images in RGB-D data, significantly improving quality and efficiency over existing techniques.

Contribution

It presents a novel iterative approach combining color-guided graph construction and graph filtering, optimized for speed by operating in the vertex domain.

Findings

Outperforms state-of-the-art depth denoising methods

Achieves higher quality in depth image restoration

Demonstrates improved computational efficiency

Abstract

Depth images captured by off-the-shelf RGB-D cameras suffer from much stronger noise than color images. In this paper, we propose a method to denoise the depth images in RGB-D images by color-guided graph filtering. Our iterative method contains two components: color-guided similarity graph construction, and graph filtering on the depth signal. Implemented in graph vertex domain, filtering is accelerated as computation only occurs among neighboring vertices. Experimental results show that our method outperforms state-of-art depth image denoising methods significantly both on quality and efficiency.