8 papers
Proxy Avatar Meets Low-Rank Caching: Real-Time One-Shot Emotion-Controllable Portrait Animation
Haijie Yang, Jindi Bao, Yixuan Dong +6
Audio-driven portrait animation has advanced rapidly with diffusion-based generative models, yet real-time one-shot generation with expressive emotion control remains challenging.…
GaussianEmoTalker: Real-Time Emotional Talking Head Synthesis with Audio-Driven and Blendshape-Based 3D Gaussian Splatting
Haijie Yang, Zhenyu Zhang, Yixuan Dong +2
Audio-driven talking head synthesis has achieved impressive progress in lip synchronization and visual quality, yet generating expressive emotional avatars with controllable intens…
Warm Chat: Diffuse Emotion-aware Interactive Talking Head Avatar with Tree-Structured Guidance
Haijie Yang, Zhenyu Zhang, Hao Tang +2
Generative models have advanced rapidly, enabling impressive talking head generation that brings AI to life. However, most existing methods focus solely on one-way portrait animati…
Spatial-Temporal Graph Mamba for Music-Guided Dance Video Synthesis
Hao Tang, Ling Shao, Zhenyu Zhang +2
We propose a novel spatial-temporal graph Mamba (STG-Mamba) for the music-guided dance video synthesis task, i.e., to translate the input music to a dance video. STG-Mamba consists…
Semantic-Guided Diffusion Model for Single-Step Image Super-Resolution
Zihang Liu, Zhenyu Zhang, Hao Tang
Diffusion-based image super-resolution (SR) methods have demonstrated remarkable performance. Recent advancements have introduced deterministic sampling processes that reduce infer…
Follow Your Motion: A Generic Temporal Consistency Portrait Editing Framework with Trajectory Guidance
Haijie Yang, Zhenyu Zhang, Hao Tang +2
Pre-trained conditional diffusion models have demonstrated remarkable potential in image editing. However, they often face challenges with temporal consistency, particularly in the…