Vision-based control of 3D facial animation
Proceedings of the 2003 ACM SIGGRAPH/Eurographics symposium on Computer animation
Proceedings of the 2003 ACM SIGGRAPH/Eurographics symposium on Computer animation
A sketching interface for articulated figure animation
Proceedings of the 2003 ACM SIGGRAPH/Eurographics symposium on Computer animation
SCA '04 Proceedings of the 2004 ACM SIGGRAPH/Eurographics symposium on Computer animation
Animal gaits from video: comparative studies
Graphical Models - Special issue on SCA 2004
Computational studies of human motion: part 1, tracking and motion synthesis
Foundations and Trends® in Computer Graphics and Vision
Video-guided motion synthesis using example motions
ACM Transactions on Graphics (TOG)
A sketching interface for articulated figure animation
ACM SIGGRAPH 2006 Courses
A survey of advances in vision-based human motion capture and analysis
Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
A sketching interface for articulated figure animation
ACM SIGGRAPH 2007 courses
Human Motion Tracking with a Kinematic Parameterization of Extremal Contours
International Journal of Computer Vision
Video-Based Motion Capturing for Skeleton-Based 3D Models
PSIVT '09 Proceedings of the 3rd Pacific Rim Symposium on Advances in Image and Video Technology
Reuse of motion capture data in animation: a review
ICCSA'03 Proceedings of the 2003 international conference on Computational science and its applications: PartIII
Towards robust 3d reconstruction of human motion from monocular video
ICAT'06 Proceedings of the 16th international conference on Advances in Artificial Reality and Tele-Existence
Human Factors in Ergonomics & Manufacturing
Motion capture and human pose reconstruction from a single-view video sequence
Digital Signal Processing
Forward non-rigid motion tracking for facial MoCap
The Visual Computer: International Journal of Computer Graphics
| Hi-index | 0.00 |
Motion capture can be an effective method of creating realistic human motion for animation. Unfortunately, the quality demands for animation place challenging demands on a capture system. To date, capture solutions that meet these demands have required specialized hardware that is invasive and expensive. Computer vision could make animation data much easier to obtain. Unfortunately, current techniques fall short of the demands of animation applications. In this paper, we will explore why the demands of animation lead to a particularly difficult challenge for capture techniques. We present a constraint-based methodology for reconstructing the 3D motion given image observations, and use this as a tool for understanding the problem. Synthetic experiments confirm that these situations would arise in practice. The experiments show how even simple visual tracking information can be used to create human motion but even with perfect tracking, incorrect reconstructions are not onlypossible but inevitable.