PUSA V1.0: Surpassing Wan-I2V with $500 Training Cost by Vectorized Timestep Adaptation
Paper • 2507.16116 • Published • 13
AI & ML interests
Video Generation
Recent Activity
View all activity
Papers
CutClaw: Agentic Hours-Long Video Editing via Music Synchronization
PersonaLive! Expressive Portrait Image Animation for Live Streaming
vinthony
authored 7
papers 3 days ago
GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors
Paper • 2508.09667 • Published • 6
MV-Performer: Taming Video Diffusion Model for Faithful and Synchronized Multi-view Performer Synthesis
Paper • 2510.07190 • Published • 1
SKEL-CF: Coarse-to-Fine Biomechanical Skeleton and Surface Mesh Recovery
Paper • 2511.20157 • Published • 3
EmoCAST: Emotional Talking Portrait via Emotive Text Description
Paper • 2508.20615 • Published
MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence
Paper • 2603.00515 • Published • 2
CutClaw: Agentic Hours-Long Video Editing via Music Synchronization
Paper • 2603.29664 • Published • 42
vinthony
submitted a
paper to Daily Papers 3 days ago
vinthony
authored a
paper 4 months ago
vinthony
authored a
paper 7 months ago
vinthony
authored 10
papers 9 months ago
LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation
Paper • 2309.09294 • Published
Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos
Paper • 2304.01186 • Published
ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models
Paper • 2310.07702 • Published
ToonTalker: Cross-Domain Face Reenactment
Paper • 2308.12866 • Published
High-Resolution Document Shadow Removal via A Large-Scale Real-World Dataset and A Frequency-Aware Shadow Erasing Net
Paper • 2308.14221 • Published • 1
SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
Paper • 2211.12194 • Published
VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild
Paper • 2211.14758 • Published • 2
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations
Paper • 2301.06052 • Published
DPE: Disentanglement of Pose and Expression for General Video Portrait Editing
Paper • 2301.06281 • Published
Noise Calibration: Plug-and-play Content-Preserving Video Enhancement using Pre-trained Video Diffusion Models
Paper • 2407.10285 • Published • 5