Abstract | ||
---|---|---|
View interpolation and image-based rendering algorithms often produce visual artifacts in regions where the 3D scene geometry is erroneous, uncertain, or incomplete. We introduce ambient point clouds constructed from colored pixels with uncertain depth, which help reduce these artifacts while providing non-photorealistic background coloring and emphasizing reconstructed 3D geometry. Ambient point clouds are created by randomly sampling colored points along the viewing rays associated with uncertain pixels. Our real-time rendering system combines these with more traditional rigid 3D point clouds and colored surface meshes obtained using multiview stereo. Our resulting system can handle larger-range view transitions with fewer visible artifacts than previous approaches. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1145/1833349.1778832 | ACM Trans. Graph. |
Keywords | Field | DocType |
real-time rendering system,scene geometry,resulting system,ambient point cloud,ambient point,larger-range view transition,point cloud,uncertain pixel,uncertain geometry,view interpolation,image-based rendering,uncertain depth,real time rendering,rendering system,image based rendering | Computer vision,Visual artifact,Colored,Polygon mesh,Computer graphics (images),Computer science,Interpolation,Pixel,Artificial intelligence,Sampling (statistics),Point cloud,Rendering (computer graphics) | Journal |
Volume | Issue | ISSN |
29 | 4 | 0730-0301 |
Citations | PageRank | References |
11 | 0.54 | 29 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Michael Goesele | 1 | 1006 | 69.58 |
Jens Ackermann | 2 | 81 | 5.17 |
Simon Fuhrmann | 3 | 157 | 8.62 |
Carsten Haubold | 4 | 11 | 0.54 |
Ronny Klowsky | 5 | 37 | 2.48 |