3 papers
cs.CV2026
MOMO: Human Motion from Moving Sounds
Deli Cai, Shuyang Xu, Zhiyang Dou +4
Human responses to sound depend not only on its semantic content, but also on the evolving spatial relationship between source and listener, conveyed through spatial audio and its…
cs.CV2026
StereoGS: Sparse-View 3D Gaussian Splatting via Stereo Priors
Wenhao Yuan, Yiyuan Ge, Deli Cai
3D Gaussian Splatting (3DGS) has achieved remarkable success in real-time novel view synthesis, yet it suffers from severe overfitting under sparse-view settings due to insufficien…
cs.CV2026
Coordinating Multiple Conditions for Trajectory-Controlled Human Motion Generation
Deli Cai, Haoyang Ma, Changxing Ding
Trajectory-controlled human motion generation aims to synthesize realistic human motions conditioned on both textual descriptions and spatial trajectories. However, existing method…