Name
Abstract | ||
|---|---|---|
Early work in computer vision considered a host of geometric cues for both shape reconstruction and recognition. However, since then, the vision community has focused heavily on shading cues for reconstruction, and moved towards data-driven approaches for recognition. In this paper, we reconsider these perhaps overlooked "boundary" cues (such as self occlusions and folds in a surface), as well as many other established constraints for shape reconstruction. In a variety of user studies and quantitative tasks, we evaluate how well these cues inform shape reconstruction (relative to each other) in terms of both shape quality and shape recognition. Our findings suggest many new directions for future research in shape reconstruction, such as automatic boundary cue detection and relaxing assumptions in shape from shading (e.g. orthographic projection, Lambertian surfaces). |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/CVPR.2013.281 | CVPR |
Keywords | Field | DocType |
3d object shape recovery,shading,shading cue,shape reconstruction,shape recognition,vision community,early work,object shape recovery,boundary cues,data-driven approach,image reconstruction,edge detection,automatic boundary cue detection,computer vision,solid modelling,shape quality,lambertian surface,surface reconstruction,shape,optimization,face | Iterative reconstruction,Active shape model,Computer vision,Pattern recognition,Orthographic projection,Computer science,Edge detection,Topological skeleton,Artificial intelligence,Photometric stereo,Shape analysis (digital geometry),3D reconstruction | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1063-6919 |
Citations | PageRank | References |
11 | 0.59 | 0 |
Authors | ||
5 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Kevin Karsch | 1 | 313 | 14.91 |
| Zicheng Liao | 2 | 289 | 14.42 |
| Jason Rock | 3 | 59 | 3.17 |
| Jonathan T. Barron | 4 | 881 | 39.55 |
| Derek Hoiem | 5 | 4998 | 302.66 |