Yulin Ren — accepted AI-conference papers

2024

MoE-DiffIR: Task-customized Diffusion Priors for Universal Compressed Image Restoration

Yulin Ren, Xin Li*, Bingchen Li, Xingrui Wang, Mengxi China Guo, Shijie Zhao +2

ECCV 2024poster

"We present MoE-DiffIR, an innovative universal compressed image restoration (CIR) method with task-customized diffusion priors. This intends to handle two pivotal challenges in the existing CIR methods: (i) lacking adaptability and universality for different image codecs, , JPEG and WebP; (ii) poor…

Cited by 8 Source ↗PDF ↗code ↗Scholar ↗

2024

UCIP: A Universal Framework for Compressed Image Super-Resolution using Dynamic Prompt

Xin Li*, Bingchen Li, Yeying Jin, Cuiling Lan, Hanxin Zhu, Yulin Ren +1

ECCV 2024poster

"Compressed Image Super-resolution (CSR) aims to simultaneously super-resolve the compressed images and tackle the challenging hybrid distortions caused by compression. However, existing works on CSR usually focus on single compression codec, , JPEG, ignoring the diverse traditional or learning-base…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗