Presentation

<
ACT: A Unified Framework for Rigging and Animating Characters with Arbitrary Topologies
SessionLearning in Motion
DescriptionACT is a unified AI framework that effortlessly brings static 3D characters to life. By integrating rigging, skinning, and motion generation into a single diffusion-based pipeline, ACT automatically animates characters of any shape, delivering high-quality, physically plausible motions that overcome the limitations of traditional, multi-step animation workflows.
Authors
Pengyu Long
ShanghaiTech University
ByteDance Games
Weirui Wang
ShanghaiTech University
Deemos Technology
Qingcheng Zhao
University of Toronto
Deemos Technology
Xiaoyang Guo
ByteDance Games
Xiaoyu Pan
ByteDance Games
Qixuan Zhang
ShanghaiTech University
Deemos Technology
Jiaqing Zhou
ByteDance Games
Tianlei Hu
ByteDance Games
Wei Yang
Huazhong University of Science and Technology
Lan Xu
ShanghaiTech University
Jingyi Yu
ShanghaiTech University
Event Type
Technical Paper
TimeThursday, 23 July 20262:50pm - 3:00pm PDT
LocationRoom 403 A
Digital Library PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Thursday, 23 July 20262:00pm - 3:30pm PDTRoom 403 A
Keywords
Animation
Artificial Intelligence/Machine Learning
Simulation
Registration Categories
Full Conference Supporter
Full Conference
Next PresentationNext PresentationLearning in Motion - Interactive Discussion
Similar Presentations
MOCHI: Motion Enhancement of Collaborative Human-object Interactions
TopoCap: Learning Topology-Agnostic Motion Priors for Monocular Video-to-Animation
Stylized Text-to-Motion Generation via Hypernetwork-Driven Low-Rank Adaptation