Yulin Ren
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yulin Ren has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Xin Li
Department of Electronic Engineer and Information Science, University of Science and Technology of China, Hefei, China
6 shared publications - Zhibo Chen
University of Science and Technology of China, Hefei, China
6 shared publications - Bingchen Li
University of Science and Technology of China
4 shared publications - Cuiling Lan
Microsoft Research Asia, Beijing, China
2 shared publications - Hanxin Zhu
University of Science and Technology of China
2 shared publications - Li Zhang
ByteDance Inc., Beijing, China
2 shared publications
Latest Publications
- Open Access
- 21 March 2026
- Published by Elsevier in SSRN Electronic Journal
MambaCSR: Dual-Interleaved Scanning for Compressed Image Super-Resolution With SSMs
We present MambaCSR, a simple but effective framework based on Mamba for thechallenging compressed image super-resolution (CSR) task. Particularly, the scanningstrategies of Mamba are crucial for effective contextual knowledge modeling in therestoration process despite it relying on selective state space modeling for all tokens. Inthis work, we propose an efficient dual-interleaved scanning paradigm (DIS) for CSR,which is composed of two scanning strategies: (i) hierarchical interleaved scanning isdesigned to comprehensively capture and utilize the most potential contextual information within an image by simultaneously taking advantage of the local window-based andsequential scanning methods; (ii) horizontal-to-vertical interleaved scanning is proposedto reduce the computational cost by leaving the redundancy between the scanning ofdifferent directions. To overcome the non-uniform compression artifacts, we also propose position-aligned cross-scale scanning to model multi-scale contextual information.Experimental results on multiple benchmarks have shown the great performance of ourMambaCSR in the compressed image super-resolution task.
- 21 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessMambaCSR: Dual-Interleaved Scanning for Compressed Image Super-Resolution With SSMs
We present MambaCSR, a simple but effective framework based on Mamba for thechallenging compressed image super-resolution (CSR) task. Particularly, the scanningstrategies of Mamba are crucial for effective contextual knowledge modeling in therestoration process despite it relying on selective state space modeling for all tokens. Inthis work, we propose an efficient dual-interleaved scanning paradigm (DIS) for CSR,which is composed of two scanning strategies: (i) hierarchical interleaved scanning isdesigned to comprehensively capture and utilize the most potential contextual information within an image by simultaneously taking advantage of the local window-based andsequential scanning methods; (ii) horizontal-to-vertical interleaved scanning is proposedto reduce the computational cost by leaving the redundancy between the scanning ofdifferent directions. To overcome the non-uniform compression artifacts, we also propose position-aligned cross-scale scanning to model multi-scale contextual information.Experimental results on multiple benchmarks have shown the great performance of ourMambaCSR in the compressed image super-resolution task.
- Top Cited Papers
- 28 August 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (11) , 8078-8108
Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey
- 28 August 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (11) , 8078-8108
Top Cited PapersDiffusion Models for Image Restoration and Enhancement: A Comprehensive Survey
- Open Access
UniMIC: Towards Universal Multi-modality Perceptual Image Compression
We present UniMIC, a universal multi-modality image compression framework, intending to unify the rate-distortion-perception (RDP) optimization for multiple image codecs simultaneously through excavating cross-modality generative priors. Unlike most existing works that need to design and optimize image codecs from scratch, our UniMIC introduces the visual codec repository, which incorporates amounts of representative image codecs and directly uses them as the basic codecs for various practical applications. Moreover, we propose multi-grained textual coding, where variable-length content prompt and compression prompt are designed and encoded to assist the perceptual reconstruction through the multi-modality conditional generation. In particular, a universal perception compensator is proposed to improve the perception quality of decoded images from all basic codecs at the decoder side by reusing text-assisted diffusion priors from stable diffusion. With the cooperation of the above three strategies, our UniMIC achieves a significant improvement of RDP optimization for different compression codecs, e.g., traditional and learnable codecs, and different compression costs, e.g., ultra-low bitrates. The code will be available in https://github.com/Amygyx/UniMIC .
Open AccessUniMIC: Towards Universal Multi-modality Perceptual Image Compression
We present UniMIC, a universal multi-modality image compression framework, intending to unify the rate-distortion-perception (RDP) optimization for multiple image codecs simultaneously through excavating cross-modality generative priors. Unlike most existing works that need to design and optimize image codecs from scratch, our UniMIC introduces the visual codec repository, which incorporates amounts of representative image codecs and directly uses them as the basic codecs for various practical applications. Moreover, we propose multi-grained textual coding, where variable-length content prompt and compression prompt are designed and encoded to assist the perceptual reconstruction through the multi-modality conditional generation. In particular, a universal perception compensator is proposed to improve the perception quality of decoded images from all basic codecs at the decoder side by reusing text-assisted diffusion priors from stable diffusion. With the cooperation of the above three strategies, our UniMIC achieves a significant improvement of RDP optimization for different compression codecs, e.g., traditional and learnable codecs, and different compression costs, e.g., ultra-low bitrates. The code will be available in https://github.com/Amygyx/UniMIC .
- 23 November 2024
- Published by Springer Nature
- p. 107-125
UCIP: A Universal Framework for Compressed Image Super-Resolution Using Dynamic Prompt
- 23 November 2024
- Published by Springer Nature
- p. 107-125
UCIP: A Universal Framework for Compressed Image Super-Resolution Using Dynamic Prompt
- 22 October 2024
- Published by Springer Nature
- p. 116-134
MoE-DiffIR: Task-Customized Diffusion Priors for Universal Compressed Image Restoration
- 22 October 2024
- Published by Springer Nature
- p. 116-134
MoE-DiffIR: Task-Customized Diffusion Priors for Universal Compressed Image Restoration
- Open Access
UCIP: A Universal Framework for Compressed Image Super-Resolution using Dynamic Prompt
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 focuses on a single compression codec, i.e., JPEG, ignoring the diverse traditional or learning-based codecs in the practical application, e.g., HEVC, VVC, HIFIC, etc. In this work, we propose the first universal CSR framework, dubbed UCIP, with dynamic prompt learning, intending to jointly support the CSR distortions of any compression codecs/modes. Particularly, an efficient dynamic prompt strategy is proposed to mine the content/spatial-aware task-adaptive contextual information for the universal CSR task, using only a small amount of prompts with spatial size 1x1. To simplify contextual information mining, we introduce the novel MLP-like framework backbone for our UCIP by adapting the Active Token Mixer (ATM) to CSR tasks for the first time, where the global information modeling is only taken in horizontal and vertical directions with offset prediction. We also build an all-in-one benchmark dataset for the CSR task by collecting the datasets with the popular 6 diverse traditional and learning-based codecs, including JPEG, HEVC, VVC, HIFIC, etc., resulting in 23 common degradations. Extensive experiments have shown the consistent and excellent performance of our UCIP on universal CSR tasks. The project can be found in https://lixinustc.github.io/UCIP.github.io
Open AccessUCIP: A Universal Framework for Compressed Image Super-Resolution using Dynamic Prompt
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 focuses on a single compression codec, i.e., JPEG, ignoring the diverse traditional or learning-based codecs in the practical application, e.g., HEVC, VVC, HIFIC, etc. In this work, we propose the first universal CSR framework, dubbed UCIP, with dynamic prompt learning, intending to jointly support the CSR distortions of any compression codecs/modes. Particularly, an efficient dynamic prompt strategy is proposed to mine the content/spatial-aware task-adaptive contextual information for the universal CSR task, using only a small amount of prompts with spatial size 1x1. To simplify contextual information mining, we introduce the novel MLP-like framework backbone for our UCIP by adapting the Active Token Mixer (ATM) to CSR tasks for the first time, where the global information modeling is only taken in horizontal and vertical directions with offset prediction. We also build an all-in-one benchmark dataset for the CSR task by collecting the datasets with the popular 6 diverse traditional and learning-based codecs, including JPEG, HEVC, VVC, HIFIC, etc., resulting in 23 common degradations. Extensive experiments have shown the consistent and excellent performance of our UCIP on universal CSR tasks. The project can be found in https://lixinustc.github.io/UCIP.github.io
- Open Access
MoE-DiffIR: Task-customized Diffusion Priors for Universal Compressed Image Restoration
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, e.g., JPEG and WebP; (ii) poor texture generation capability, particularly at low bitrates. Specifically, our MoE-DiffIR develops the powerful mixture-of-experts (MoE) prompt module, where some basic prompts cooperate to excavate the task-customized diffusion priors from Stable Diffusion (SD) for each compression task. Moreover, the degradation-aware routing mechanism is proposed to enable the flexible assignment of basic prompts. To activate and reuse the cross-modality generation prior of SD, we design the visual-to-text adapter for MoE-DiffIR, which aims to adapt the embedding of low-quality images from the visual domain to the textual domain as the textual guidance for SD, enabling more consistent and reasonable texture generation. We also construct one comprehensive benchmark dataset for universal CIR, covering 21 types of degradations from 7 popular traditional and learned codecs. Extensive experiments on universal CIR have demonstrated the excellent robustness and texture restoration capability of our proposed MoE-DiffIR. The project can be found at https://renyulin-f.github.io/MoE-DiffIR.github.io/.
Open AccessMoE-DiffIR: Task-customized Diffusion Priors for Universal Compressed Image Restoration
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, e.g., JPEG and WebP; (ii) poor texture generation capability, particularly at low bitrates. Specifically, our MoE-DiffIR develops the powerful mixture-of-experts (MoE) prompt module, where some basic prompts cooperate to excavate the task-customized diffusion priors from Stable Diffusion (SD) for each compression task. Moreover, the degradation-aware routing mechanism is proposed to enable the flexible assignment of basic prompts. To activate and reuse the cross-modality generation prior of SD, we design the visual-to-text adapter for MoE-DiffIR, which aims to adapt the embedding of low-quality images from the visual domain to the textual domain as the textual guidance for SD, enabling more consistent and reasonable texture generation. We also construct one comprehensive benchmark dataset for universal CIR, covering 21 types of degradations from 7 popular traditional and learned codecs. Extensive experiments on universal CIR have demonstrated the excellent robustness and texture restoration capability of our proposed MoE-DiffIR. The project can be found at https://renyulin-f.github.io/MoE-DiffIR.github.io/.