Phase-aware candidate selection for time-of-flight depth map denoising

Hach, Thomas; Seybold, Tamara; Böttcher, Hendrik

doi:10.1117/12.2076622

Cited by 2 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, we decided to use a dynamic RGBD ground truth sequences from the dataset provided by Richardt et al (Richardt, Orr, Davies, & Criminisi, 2010), including computer-generated matching RGB images and depth maps. For evaluation of denoising we add zero-mean white Gaussian noise in several experiments with increasing noise standard deviations, which have been chosen to compare to realistic noise levels (Hach & Steurer, 2013), (Hach, Seybold, & Böttcher, 2015b).…”

Section: Ground Truth Datamentioning

confidence: 99%

Spatio-Temporal Denoising for Depth Map Sequences

Hach

Seybold

2016

International Journal of Multimedia Data Engineering and Management

Self Cite

View full text Add to dashboard Cite

This paper proposes a novel strategy for depth video denoising in RGBD camera systems. Depth map sequences obtained by state-of-the-art Time-of-Flight sensors suffer from high temporal noise. Hence, all high-level RGB video renderings based on the accompanied depth maps' 3D geometry like augmented reality applications will have severe temporal flickering artifacts. The authors approached this limitation by decoupling depth map upscaling from the temporal denoising step. Thereby, denoising is processed on raw pixels including uncorrelated pixel-wise noise distributions. The authors' denoising methodology utilizes joint sparse 3D transform-domain collaborative filtering. Therein, they extract RGB texture information to yield a more stable and accurate highly sparse 3D depth block representation for the consecutive shrinkage operation. They show the effectiveness of our method on real RGBD camera data and on a publicly available synthetic data set. The evaluation reveals that the authors' method is superior to state-of-the-art methods. Their method delivers flicker-free depth video streams for future applications.

show abstract

Section: Ground Truth Datamentioning

confidence: 99%