Abstract | ||
---|---|---|
In this paper, we propose a temporal filtering algorithm to obtain the temporally consistent depth video. We apply a joint multilateral filter to depth video that is based on three Gaussian distributions: one spatial filter and two range filters for color and depth similarities. We also perform outlier reduction in the temporal domain using Gaussian-weighted least squares fitting method to deal with temporal displacement. Experimental results show that the proposed method improves depth quality by 1.22 dB on average, compared to other algorithms due to enhanced temporal consistency. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1007/s11760-014-0642-7 | Signal, Image and Video Processing |
Keywords | Field | DocType |
Depth video filter, Joint multilateral filter, Gaussian-weighted least squares, Temporal consistency, Three-dimensional video | Least squares,Computer vision,Filter (video),Pattern recognition,Outlier,Filter (signal processing),Gaussian,Artificial intelligence,Temporal consistency,Mathematics,Spatial filter | Journal |
Volume | Issue | ISSN |
9 | 6 | 1863-1711 |
Citations | PageRank | References |
1 | 0.35 | 9 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sang-Beom Lee | 1 | 30 | 2.85 |
Yo-Sung Ho | 2 | 1288 | 146.57 |