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

1 citations · 1 across the 4 of their papers we have counts for

collaborators

5 papers

cs.CV2026

NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models: Datasets, Methods and Results

Xin Li, Jiachao Gong, Xijun Wang +75

This paper presents an overview of the NTIRE 2026 Challenge on Short-form UGC Video Restoration in the Wild with Generative Models. This challenge utilizes a new short-form UGC (S-…

eess.IV2024

UniMIC: Towards Universal Multi-modality Perceptual Image Compression

Yixin Gao, Xin Li, Xiaohan Pan +5

We present UniMIC, a universal multi-modality image compression framework, intending to unify the rate-distortion-perception (RDP) optimization for multiple image codecs simultaneo…

cs.CV2024

MambaCSR: Dual-Interleaved Scanning for Compressed Image Super-Resolution With SSMs

Yulin Ren, Xin Li, Mengxi Guo +3

We present MambaCSR, a simple but effective framework based on Mamba for the challenging compressed image super-resolution (CSR) task. Particularly, the scanning strategies of Mamb…

cs.CV20241 cited

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

Xin Li, Bingchen Li, Yeying Jin +4

Compressed Image Super-resolution (CSR) aims to simultaneously super-resolve the compressed images and tackle the challenging hybrid distortions caused by compression. However, exi…

eess.IV2024

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

Yulin Ren, Xin Li, Bingchen Li +5

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…