Presentation

<
ELGAR: Expressive Cello Performance Motion Generation for Audio Rendition
SessionMotion From X
DescriptionGenerating string instrument performances with intricate movements and complex interactions poses significant challenges. To address these, we present ELGAR—the first diffusion-based framework for whole-body instrument performance motion generation solely from audio. We further contribute innovative losses, metrics, and dataset, marking a novel attempt with promising results for this emerging task.
Authors
Zhiping Qiu
Central Conservatory of Music
Tsinghua University
Yitong Jin
Central Conservatory of Music
Tsinghua University
Yuan Wang
Central Conservatory of Music
Yi Shi
Central Conservatory of Music
Tsinghua University
Chao Tan
Weilan Tech
Chongwu Wang
Central Conservatory of Music
Xiaobing Li
Central Conservatory of Music
Feng Yu
Central Conservatory of Music
Tao Yu
Tsinghua University
Qionghai Dai
Tsinghua University
Event Type
Technical Paper
TimeTuesday, 12 August 202511:05am - 11:15am 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 PresentationMotion-example-controlled Co-speech Gesture Generation Leveraging Large Language Models
Similar Presentations
AutoKeyframe: Autoregressive Keyframe Generation for Human Motion Synthesis and Editing
Motion Control via Metric-Aligning Motion Matching
PLT: Part-Wise Latent Tokens as Adaptable Motion Priors for Physically Simulated Characters