5 papers
Improving Reconstruction of Representation Autoencoder
Siyu Liu, Chujie Qin, Hubery Yin +6
Recent work leverages Vision Foundation Models as image encoders to boost the generative performance of latent diffusion models (LDMs), as their semantic feature distributions are…
PerTouch: VLM-Driven Agent for Personalized and Semantic Image Retouching
Zewei Chang, Zheng-Peng Duan, Jianxing Zhang +6
Image retouching aims to enhance visual quality while aligning with users' personalized aesthetic preferences. To address the challenge of balancing controllability and subjectivit…
A Diffusion-Based Framework for Occluded Object Movement
Zheng-Peng Duan, Jiawei Zhang, Siyu Liu +5
Seamlessly moving objects within a scene is a common requirement for image editing, but it is still a challenge for existing editing methods. Especially for real-world images, the…
Iterative Predictor-Critic Code Decoding for Real-World Image Dehazing
Jiayi Fu, Siyu Liu, Zikun Liu +5
We propose a novel Iterative Predictor-Critic Code Decoding framework for real-world image dehazing, abbreviated as IPC-Dehaze, which leverages the high-quality codebook prior enca…
FaceMe: Robust Blind Face Restoration with Personal Identification
Siyu Liu, Zheng-Peng Duan, Jia OuYang +5
Blind face restoration is a highly ill-posed problem due to the lack of necessary context. Although existing methods produce high-quality outputs, they often fail to faithfully pre…