2 papers
cs.CV2026
Neural Video Compression with Domain Transfer
Tiange Zhang, Rongqun Lin, Xiandong Meng +4
Content-adaptive compression has always been a key direction in neural video coding (NVC), aiming to mitigate the domain gap between training and testing data. Such gaps often aris…
cs.CV2024
Consistent Diffusion: Denoising Diffusion Model with Data-Consistent Training for Image Restoration
Xinlong Cheng, Tiantian Cao, Guoan Cheng +7
In this work, we address the limitations of denoising diffusion models (DDMs) in image restoration tasks, particularly the shape and color distortions that can compromise image qua…