Published in IEEE Transactions on Image Processing (TIP), 2025
A multi-functional VLM-based IQA model with a 495K large-scale dataset, surpassing GPT-4V
Download here
Published in IEEE Transactions on Multimedia (TMM), 2025
An efficient three-step SDRTV-to-HDRTV conversion method with only 35K parameters for global color mapping
Download here
Published in International Conference on Learning Representations (ICLR), 2025
Unidirectional information flow reduces GPU memory by 1/3 and speeds up training by 2.3x for diffusion model control
Download here
Published in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025
Introduce causality theory to interpret low-level vision models with a model-/task-agnostic method
Download here
Published in European Conference on Computer Vision (ECCV), 2024
Propose a general backbone for image restoration
Download here
Published in European Conference on Computer Vision (ECCV), 2024
Propose a language-based image quality assessment method
Download here
Published in Conference on Computer Vision and Pattern Recognition, 2024
The most powerful image restoration and enhancement tool that is nearly ready for commercial use
Download here
Published in European Conference on Computer Vision (ECCV) workshops, 2022
ECCV workshop
Download here
Published in Journal of Integration Technology, 2022
A survey on Single Image Super-Resolution
Download here
Published in Computer Vision and Pattern Recognition (CVPR) Workshops, 2022
Winner in NTIRE 2022 Efficient SR sub-track: Model Complexity
Download here