Presentation

<
Semantically Consistent Text-to-Motion with Unsupervised Styles
SessionMotion From X
DescriptionWe introduce a novel method that integrates unsupervised style from arbitrary references into a text-driven diffusion model to generate semantically consistent stylized human motion. We leverage text as a mediator to capture the temporal correspondences between motion and style, enabling the seamless integration of temporally dynamic style into motion features.
Authors
Linjun Wu
Zhejiang University
State Key Laboratory of CAD&CG, Zhejiang University
Xiangjun Tang
Zhejiang University
State Key Laboratory of CAD&CG, Zhejiang University
Jingyuan Cong
University of California San Diego
He Wang
UCL Centre for Artificial Intelligence, Department of Computer Science, University College London (UCL)
Bo Hu
Tencent Technology (Shenzhen) Co., Ltd.
Xu Gong
Tencent Technology (Shenzhen) Co., Ltd.
Songnan Li
Tencent Technology (Shenzhen) Co., Ltd.
Yuchen Liao
Tencent Technology (Shenzhen) Co., Ltd.
Yiqian Wu
Zhejiang University
Chen Liu
State Key Lab of CAD and CG, Zhejiang University
Xiaogang Jin
Zhejiang University
State Key Laboratory of CAD&CG, Zhejiang University
Event Type
Technical Paper
TimeTuesday, 12 August 202511:25am - 11:35am PDT
LocationWest Building, Rooms 220-222
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 10 August 20256:00pm - 8:45pm PDTWest Building, Ballroom AB
Tuesday, 12 August 202510:45am - 12:15pm PDTWest Building, Rooms 220-222
Recordings
Livestreamed
Recorded
Next PresentationNext PresentationSketch2Anim: Towards Transferring Sketch Storyboards into 3D Animation
Similar Presentations
AutoKeyframe: Autoregressive Keyframe Generation for Human Motion Synthesis and Editing
Motion Control via Metric-Aligning Motion Matching
Model See Model Do: Speech-Driven Facial Animation with Style Control