DiffBody: Human Body Restoration by Imagining with Generative Diffusion Prior
This work addresses human body restoration for applications involving human images, representing an incremental improvement by adapting diffusion models with domain-specific enhancements.
The paper tackles the problem of human body restoration in images, where existing generative models often produce blending, over-smoothing, missing details, and distortions. The proposed method uses a human body-aware diffusion model with domain-specific guidance, achieving superior quantitative and qualitative results over existing approaches.
Human body restoration plays a vital role in various applications related to the human body. Despite recent advances in general image restoration using generative models, their performance in human body restoration remains mediocre, often resulting in foreground and background blending, over-smoothing surface textures, missing accessories, and distorted limbs. Addressing these challenges, we propose a novel approach by constructing a human body-aware diffusion model that leverages domain-specific knowledge to enhance performance. Specifically, we employ a pretrained body attention module to guide the diffusion model's focus on the foreground, addressing issues caused by blending between the subject and background. We also demonstrate the value of revisiting the language modality of the diffusion model in restoration tasks by seamlessly incorporating text prompt to improve the quality of surface texture and additional clothing and accessories details. Additionally, we introduce a diffusion sampler tailored for fine-grained human body parts, utilizing local semantic information to rectify limb distortions. Lastly, we collect a comprehensive dataset for benchmarking and advancing the field of human body restoration. Extensive experimental validation showcases the superiority of our approach, both quantitatively and qualitatively, over existing methods.