Abstract

4D Video Textures (4DVT) introduce a novel representation for rendering video-realistic interactive character animation from a database of 4D actor performance captured in a multiple camera studio. 4D performance capture reconstructs dynamic shape and appearance over time but is limited to free-viewpoint video replay of the same motion. Interactive animation from 4D performance capture has so far been limited to surface shape only. 4DVT is the final piece in the puzzle enabling video-realistic interactive animation through two contributions: a layered view-dependent texture map representation which supports efficient storage, transmission and rendering from multiple view video capture; and a rendering approach that combines multiple 4DVT sequences in a parametric motion space, maintaining video quality rendering of dynamic surface appearance whilst allowing high-level interactive control of character motion and viewpoint. 4DVT is demonstrated for multiple characters and evaluated both quantitatively and through a user-study which confirms that the visual quality of captured video is maintained. The 4DVT representation achieves >90% reduction in size and halves the rendering cost.

Paper

4D Video Textures for Interactive Character Appearance
Dan Casas, Marco Volino, John Collomosse and Adrian Hilton
Proceedings of EUROGRAPHICS 2014

Data

The source of the datasets should be acknowledged in all publications in which it is used as by referencing the following paper and this web-site: Casas, D., Volino, M., Collomosse, J. and Hilton, A. "4D Video Textures for Interactive Character Appearance", Computer Graphics Forum (Proceedings of Eurographics 2014) 33(2):xx-yy, 2014.

Please, send an email to to obtain the password to download the data.

Dataset Dan

Walk ‒ 29 frames ‒ 8 cameras
Jog ‒ 20 frames ‒ 8 cameras
Left turn ‒ 27 frames ‒ 8 cameras
Right turn ‒ 27 frames ‒ 8 cameras
Low jump ‒ 18 frames ‒ 8 cameras
High jump ‒ 31 frames ‒ 8 cameras
Short jump ‒ 36 frames ‒ 8 cameras
Long jump ‒ 53 frames ‒ 8 cameras
Small box low ‒ 171 frames ‒ 8 cameras
Big box low ‒ 162 frames ‒ 8 cameras

Dataset Infantry

Walk ‒ 30 frames ‒ 10 cameras
Jog ‒ 22 frames ‒ 10 cameras
Left turn ‒ 32 frames ‒ 10 cameras
Right turn ‒ 55 frames ‒ 10 cameras
Low jump ‒ 24 frames ‒ 10 cameras
High jump ‒ 34 frames ‒ 10 cameras
Short jump ‒ 42 frames ‒ 10 cameras
Long jump ‒ 50 frames ‒ 10 cameras
Walk to stand ‒ 50 frames ‒ 10 cameras
Stand to walk ‒ 21 frames ‒ 10 cameras

Dataset Knight

Walk ‒ 29 frames ‒ 10 cameras
Calibration
Images
Silhouettes
Meshes
Run ‒ 18 frames ‒ 10 cameras
Calibration
Images
Silhouettes
Meshes
Left turn ‒ 27 frames ‒ 10 cameras
Calibration
Images
Silhouettes
Meshes

Acknowledgments

The work presented here was carried out as a part of the EU-funded FP7 project RE@CT, grant no. 288369.