Zhaofan Qiu

6

Papers

24

Total Citations

Papers (6)

MotionPro: A Precise Motion Controller for Image-to-Video Generation

Ouroboros-Diffusion: Exploring Consistent Content Generation in Tuning-free Long Video Diffusion

Denoising Token Prediction in Masked Autoregressive Models

Aligning Global Semantics and Local Textures in Generative Video Enhancement

TRIP: Temporal Residual Learning with Image Noise Prior for Image-to-Video Diffusion Models

Learning Spatial Adaptation and Temporal Coherence in Diffusion Models for Video Super-Resolution