Social-Event-Driven Camera Control for
Multi-Character Animations

I-Cheng Yeh     Wen-Chieh Lin     Tong-Yee Lee     Hsin-Ju Han     Jehee Lee     Manmyung Kim

to appear in IEEE Transactions on Visualization and Computer Graphics

Teaser Our camera control discovers and analyzes important events in a multi-character animation to generate a motion overview automatically.

Abstract

In a virtual world, a group of virtual characters can interact with each other, another. The interaction among individuals and groups often produces interesting events in a sequence of animation. The goal of this paper is to discover social events involving mutual interactions or group activities in multi-character animations and automatically plan a smooth camera motion to view interesting events suggested by our system or relevant events specified by a user. Inspired by sociology studies, we borrow the knowledge in Proxemics, social force, and social network analysis to model the dynamic relation among social events and the relation among the participants within each event. By analyzing the variation of relation strength among participants and spatiotemporal correlation among events, we discover salient social events in a motion clip and generate an overview video of these events with smooth camera motion using a simulated annealing optimization method. We tested our approach on different motions performed by multiple characters. Our user study shows that our results are preferred in 66.19% of the comparisons with those by the camera control approach without event analysis and are comparable (51.79%) to professional results by an artist.

Paper
Download

PDF, 33.24MB
(Adobe PDF, Paper: 33.24MB, Download from IEEE Xplore [Comming soon], Our draft vision [Link])

Illustrative video
Results
BibTeX

@article{SEDCC_NCA12,
   author    = {I-Cheng Yeh and Wen-Chieh Lin and Tong-Yee Lee
                and Hsin-Ju Han and Jehee Lee and Manmyung Kim},
   title     = {Social-Event-Driven Camera Control for Multi-Character Animations},
   journal   = {IEEE Transactions on Visualization and Computer Graphics},
   volume    = {99},
   number    = {PrePrints},
   issn      = {1077-2626},
   year      = {2011},
   doi       = {http://doi.ieeecomputersociety.org/10.1109/TVCG.2011.273},
   publisher = {IEEE Computer Society},
   address   = {Los Alamitos, CA, USA},
}