Adaptive colour‐guided non‐local means algorithm for compound noise reduction of depth maps. Issue 12 (11th September 2020)

• Record Type: Journal Article
• Authors: Ibrahim, Mostafa M.; Liu, Qiong; Yang, You
• Is Part Of: IET image processing. Volume 14:Issue 12(2020)
• Page Start: 2768
• Page End: 2779
• Publication Date: 2020-09-11
• Subjects: image reconstruction -- image restoration -- image denoising -- image texture -- image colour analysis -- image filtering -- stereo image processing -- image representation -- adaptive filters; adaptive colour‐guided nonlocal means algorithm -- compound noise reduction -- object positioning information -- compound noise -- subsequent filter design -- adaptive colour‐guided nonlocal mean filter -- nonhole pixels -- restored depth map edges -- interactive visual applications -- RGB‐D data representation -- active illumination shadows -- colour image -- hole‐artifact removal -- virtual view synthesis -- 3D scene reconstruction; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2019.0074
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Depth maps are used to describe object positioning information in three‐dimensional (3D) space, and they are crucial for RGB‐D data representation, which is useful for numerous interactive visual applications. In practice, depth maps are often contaminated by compound noise, including intrinsic noise and missing regions owing to active illumination shadows. As existing noise models cannot describe the above‐mentioned compound noise effectively, the subsequent filter design is a challenging task. In this study, an adaptive colour‐guided non‐local mean (NLM) filter is proposed to address such compound noise. First, the authors classify the depth map into hole and non‐hole pixels. Then, the proposed filter is designed on the basis of the NLM framework, where the colour image is used as a guide prior for hole‐artifact removal. Finally, the authors use a shock filter to effectively address the non‐regularisation of the restored depth map edges and remove the remaining noise. Experiments show that the proposed filter qualitatively and quantitatively outperforms existing colour‐guided and unguided filters. Moreover, the authors verify the superiority of the proposed filter through virtual view synthesis and 3D scene reconstruction applications.