3 papers
cs.CV2025
DeblurDiff: Real-World Image Deblurring with Generative Diffusion Models
Lingshun Kong, Jiawei Zhang, Dongqing Zou +4
Diffusion models have achieved significant progress in image generation. The pre-trained Stable Diffusion (SD) models are helpful for image deblurring by providing clear image prio…
cs.CV2024
Semantic Segmentation Prior for Diffusion-Based Real-World Super-Resolution
Jiahua Xiao, Jiawei Zhang, Dongqing Zou +3
Real-world image super-resolution (Real-ISR) has achieved a remarkable leap by leveraging large-scale text-to-image models, enabling realistic image restoration from given recognit…
cs.CV2024
DiffRetouch: Using Diffusion to Retouch on the Shoulder of Experts
Zheng-Peng Duan, Jiawei zhang, Zheng Lin +4
Image retouching aims to enhance the visual quality of photos. Considering the different aesthetic preferences of users, the target of retouching is subjective. However, current re…