Presentation

<
MACE-Dance: Motion-Appearance Cascaded Experts for Music-Driven Dance Video Generation
SessionDigital Humans & Virtual Try-On
DescriptionMACE-Dance generates dance videos from music using cascaded motion and appearance experts. It first produces expressive 3D dance motion from music, then animates a reference image into a temporally coherent video. The paper also introduces MA-Data, a large-scale dataset and evaluation protocol for this task.
Authors
Kaixing Yang
Renmin University of China
Jiashu Zhu
Alibaba Group
AMAP
Xulong Tang
Malou Tech Inc
Ziqiao Peng
Renmin University of China
Xiangyue Zhang
Wuhan University
Puwei Wang
Renmin University of China
Jiahong Wu
Alibaba Group
AMAP
Xiangxiang Chu
Alibaba Group
AMAP
Hongyan Liu
Tsinghua University
Jun He
Renmin University of China
Event Type
Technical Paper
TimeMonday, 20 July 20269:20am - 9:30am PDT
LocationRoom 403 B
Digital Library PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Monday, 20 July 20269:00am - 10:15am PDTRoom 403 B
Keywords
Animation
Generative AI
Modeling
Registration Categories
Full Conference Supporter
Full Conference
Next PresentationNext PresentationComposing People Together: Iterative Pose-Image Generation for Multi-Person Interaction Scenes
Similar Presentations
MOCHI: Motion Enhancement of Collaborative Human-object Interactions
DreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learning
Stylized Text-to-Motion Generation via Hypernetwork-Driven Low-Rank Adaptation