8 papers · 1 filter
Bridging Fidelity-Reality with Controllable One-Step Diffusion for Image Super-Resolution
Hao Chen, Junyang Chen, Jinshan Pan +1
Recent diffusion-based one-step methods have shown remarkable progress in the field of image super-resolution, yet they remain constrained by three critical limitations: (1) inferi…
Bi-Erasing: A Bidirectional Framework for Concept Removal in Diffusion Models
Hao Chen, Yiwei Wang, Songze Li
Concept erasure, which fine-tunes diffusion models to remove undesired or harmful visual concepts, has become a mainstream approach to mitigating unsafe or illegal image generation…
Enhancing Diffusion-based Restoration Models via Difficulty-Adaptive Reinforcement Learning with IQA Reward
Xiaogang Xu, Ruihang Chu, Jian Wang +6
Reinforcement Learning (RL) has recently been incorporated into diffusion models, e.g., tasks such as text-to-image. However, directly applying existing RL methods to diffusion-bas…
Image Tokenizer Needs Post-Training
Kai Qiu, Xiang Li, Hao Chen +7
Recent image generative models typically capture the image distribution in a pre-constructed latent space, relying on a frozen image tokenizer. However, there exists a significant…
Two-Way Garment Transfer: Unified Diffusion Framework for Dressing and Undressing Synthesis
Angang Zhang, Fang Deng, Hao Chen +2
While recent advances in virtual try-on (VTON) have achieved realistic garment transfer to human subjects, its inverse task, virtual try-off (VTOFF), which aims to reconstruct cano…
Masked Autoencoders Are Effective Tokenizers for Diffusion Models
Hao Chen, Yujin Han, Fangyi Chen +7
Recent advances in latent diffusion models have demonstrated their effectiveness for high-resolution image synthesis. However, the properties of the latent space from tokenizer for…