Kaisiyuan Wang

7

Papers

11

Total Citations

Papers (7)

Re-HOLD: Video Hand Object Interaction Reenactment via adaptive Layout-instructed Diffusion Model

AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers

GestureHYDRA: Semantic Co-speech Gesture Synthesis via Hybrid Modality Diffusion Transformer and Cascaded-Synchronized Retrieval-Augmented Generation

LTA-PCS: Learnable Task-Agnostic Point Cloud Sampling

Audio-Driven Emotional Video Portraits

StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-Based Generator

ObjectSDF++: Improved Object-Compositional Neural Implicit Surfaces