Abstract | ||
---|---|---|
Scene surface exists some occlusions by mutual occlusions or self-occlusions, and then this phenomenon will serious influences 3D vision technique. We present a signal-processing framework to study occlusions of scene. Our method combines discontinuities and establish a mathematical model of occlusion phenomenon. The influences of occlusion on a scene are derived using Fourier theory. In this manner, spectral support of scene occlusion is analyzed in frequency field. Predictions on the frequency content can then be used to control the sampling and rendering in a scene. This extends previous work that the sampling and rendering to be analyzed and estimated for 3D technique. Extensive experimental evaluation demonstrates that our occlusion analysis method significantly outperform competing algorithms. |
Year | Venue | Keywords |
---|---|---|
2017 | 2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP) | Spectrum analysis, image-based rendering, occlusion, sampling, view rendering |
Field | DocType | ISSN |
Computer vision,Classification of discontinuities,Occlusion,Pattern recognition,Computer science,Bandwidth (signal processing),Artificial intelligence,Sampling (statistics),Fourier theory,Rendering (computer graphics),3d vision | Conference | 1522-4880 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Changjian Zhu | 1 | 4 | 3.15 |
Hong Zhang | 2 | 276 | 26.98 |
Li Yu | 3 | 283 | 48.76 |