4 papers
Super-resolving Real-world Image Illumination Enhancement: A New Dataset and A Conditional Diffusion Model
Yang Liu, Yaofang Liu, Jinshan Pan +4
Most existing super-resolution methods and datasets have been developed to improve the image quality in well-lighted conditions. However, these methods do not work well in real-wor…
Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach
Yaofang Liu, Yumeng Ren, Xiaodong Cun +5
Diffusion models have revolutionized image generation, and their extension to video generation has shown promise. However, current video diffusion models~(VDMs) rely on a scalar ti…
EvalCrafter: Benchmarking and Evaluating Large Video Generation Models
Yaofang Liu, Xiaodong Cun, Xuebo Liu +7
The vision and language generative models have been overgrown in recent years. For video generation, various open-sourced models and public-available services have been developed t…
VJT: A Video Transformer on Joint Tasks of Deblurring, Low-light Enhancement and Denoising
Yuxiang Hui, Yang Liu, Yaofang Liu +4
Video restoration task aims to recover high-quality videos from low-quality observations. This contains various important sub-tasks, such as video denoising, deblurring and low-lig…