• Kenneth Chen
  New York University
• Norman I. Badler
  Cesium

 

paper 

Abstract

There has recently been an explosion of interest in creating large-scale shared virtual spaces for multiplayer content. However, rendering player-controllable avatars in real-time creates latency issues when scaling to thousands of players. We introduce a human audience video dataset to support applications in deep learning-based 2D video audience simulation, bypassing the need for background 3D virtual humans. This dataset consists of YouTube videos that depict audiences with diverse lighting conditions, color, dress, and movement patterns. We describe the dataset statistics, our implicit data collection strategy, and audience video extraction pipeline. We apply deep learning tasks on this data based on video prediction techniques, and propose a novel method for 2D audience simulations.

Downloads

paper

Citation

@inproceedings{
 chen2023towards,
 author = {Chen, Kenneth and Badler, Norman},
 title = {Towards Learning and Generating Audience Motion from Video},
 year = {2023},
 url = {https://doi.org/10.1145/3606037.3606839},
 booktitle = {Proceedings of the ACM SIGGRAPH/Eurographics Symposium on Computer Animation},
 articleno = {4},
 numpages = {2},
 series = {SCA '23}
 }