7 papers
ResGVC: Residual Coding for High-fidelity Generative Video Compression
Ding Ding, Daowen Li, Ying Chen +1
Generative video compression (GVC) methods usually employ decoder-side diffusion models to denoise reconstructed signals based on generative priors. Besides, most of these methods…
Generative Video Compression Based on Hierarchical Referencing
Daowen Li, Ding Ding, Zifu Zhang +2
Diffusion-based generative video compression has emerged as a promising paradigm to improve perceptual quality, where latent frames are required to be encoded efficiently while ser…
Dense-Prior-Guided Generative Video Compression
Ding Ding, Daowen Li, Ying Chen +4
Diffusion-based generative video compression offers a promising paradigm for low-bitrate reconstruction, but existing keyframe-based controllable approaches rely on sparse priors f…
ProGVC: Progressive-based Generative Video Compression via Auto-Regressive Context Modeling
Daowen Li, Ruixiao Dong, Kai Li +3
Perceptual video compression leverages generative priors to reconstruct realistic textures and motions at low bitrates. However, existing perceptual codecs often lack native suppor…
Rethinking Diffusion Model-Based Video Super-Resolution: Leveraging Dense Guidance from Aligned Features
Jingyi Xu, Meisong Zheng, Ying Chen +3
Diffusion model (DM) based Video Super-Resolution (VSR) approaches achieve impressive perceptual quality. However, they suffer from error accumulation, spatial artifacts, and a tra…
NTIRE 2025 Challenge on UGC Video Enhancement: Methods and Results
Nikolay Safonov, Alexey Bryncev, Andrey Moskalenko +28
This paper presents an overview of the NTIRE 2025 Challenge on UGC Video Enhancement. The challenge constructed a set of 150 user-generated content videos without reference ground…
Enhancing Quality of Compressed Images by Mitigating Enhancement Bias Towards Compression Domain
Qunliang Xing, Mai Xu, Shengxi Li +4
Existing quality enhancement methods for compressed images focus on aligning the enhancement domain with the raw domain to yield realistic images. However, these methods exhibit a…