Name
Abstract | ||
|---|---|---|
This article proposes a real-time method that uses a single-view RGB-D input (a depth sensor integrated with a color camera) to simultaneously reconstruct a casual scene with a detailed geometry model, surface albedo, per-frame non-rigid motion, and per-frame low-frequency lighting, without requiring any template or motion priors. The key observation is that accurate scene motion can be used to integrate temporal information to recover the precise appearance, whereas the intrinsic appearance can help to establish true correspondence in the temporal domain to recover motion. Based on this observation, we first propose a shading-based scheme to leverage appearance information for motion estimation. Then, using the reconstructed motion, a volumetric albedo fusing scheme is proposed to complete and refine the intrinsic appearance of the scene by incorporating information from multiple frames. Since the two schemes are iteratively applied during recording, the reconstructed appearance and motion become increasingly more accurate. In addition to the reconstruction results, our experiments also show that additional applications can be achieved, such as relighting, albedo editing, and free-viewpoint rendering of a dynamic scene, since geometry, appearance, and motion are all reconstructed by our technique. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1145/3083722 | ACM Trans. Graph. |
Keywords | DocType | Volume |
Single-view,surface reconstruction,real-time,non-rigid,albedo | Journal | 36 |
Issue | ISSN | Citations |
3 | 0730-0301 | 36 |
PageRank | References | Authors |
0.87 | 31 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Kaiwen Guo | 1 | 42 | 2.68 |
| Feng Xu | 2 | 194 | 23.14 |
| Tao Yu | 3 | 41 | 2.67 |
| Xiaoyang Liu | 4 | 36 | 0.87 |
| Qionghai Dai | 5 | 3904 | 215.66 |
| Yebin Liu | 6 | 688 | 49.05 |