EDITBRIDGE: Towards Faithful and Efficient Ultra-High-Resolution Image Editing
Paper • 2608.18063 • Published • 23
Haozhong Xiong
xhznju
·
AI & ML interests
Computer Vision, Generative Video, Animatable Avatars
Recent Activity
upvoted a paper about 2 months ago
EDITBRIDGE: Towards Faithful and Efficient Ultra-High-Resolution Image Editing commentedon a paper about 2 months ago
DSAR: Dual-Stream Autoregressive Modeling of Temporal Cloth Dynamics for Photorealistic Animatable Avatars authored a paper about 2 months ago
DSAR: Dual-Stream Autoregressive Modeling of Temporal Cloth Dynamics for Photorealistic Animatable AvatarsOrganizations
upvoted a paper about 2 months ago
commented a
paper about 2 months ago
authored 4
papers about 2 months ago
DSAR: Dual-Stream Autoregressive Modeling of Temporal Cloth Dynamics for Photorealistic Animatable Avatars
Paper • 2608.10500 • Published
UniSwap: Streaming Audio-Visual Identity Swapping for Talking Videos
Paper • 2608.11752 • Published • 23
LiveAnimate: Stable Long-Form Streaming Human Animation in Real-Time
Paper • 2608.11745 • Published • 25
Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation
Paper • 2607.24731 • Published • 47
upvoted a paper about 2 months ago