Spatio-Temporal Registration Techniques for Relightable 3D Video
By jointly applying a model-based marker-less motion capture approach and multi-view texture generation 3D Videos of human actors can be reconstructed from multi-view video streams. If the input data were recorded under calibrated lighting, the texture information can also be used to measure time-varying surface reflectance. This way, 3D videos can be realistically displayed under novel lighting conditions. Reflectance estimation is only feasible if the multi-view textureto-surface registration is consistent over time. In this paper, we propose two image-based warping methods that compensate registration errors due to inaccurate model geometry and shifting of apparel over the body.
| Author(s): | Naveed Ahmed, Christian Theobalt, Marcus Magnor, Hans-Peter Seidel |
|---|---|
| Published: | September 2007 |
| Type: | Article in conference proceedings |
| Book: | Proc. IEEE International Conference on Image Processing (ICIP) |
| Presented at: | IEEE International Conference on Image Processing (ICIP) |
@inproceedings{ahmed20073dvideo,
title = {Spatio-Temporal Registration Techniques for Relightable 3D Video},
author = {Ahmed, Naveed and Theobalt, Christian and Magnor, Marcus and Seidel, Hans-Peter},
booktitle = {Proc. {IEEE} International Conference on Image Processing ({ICIP})},
month = {Sep},
year = {2007}
}
Authors
-
Naveed Ahmed
External -
Christian Theobalt
External -
Marcus Magnor
Director, Chair -
Hans-Peter Seidel
External