|国家预印本平台
首页|PrefPaint: Enhancing Image Inpainting through Expert Human Feedback

PrefPaint: Enhancing Image Inpainting through Expert Human Feedback

PrefPaint: Enhancing Image Inpainting through Expert Human Feedback

来源:Arxiv_logoArxiv
英文摘要

Inpainting, the process of filling missing or corrupted image parts, has broad applications, including medical imaging. However, in specialized fields like medical polyps imaging, where accuracy and reliability are critical, inpainting models can generate inaccurate images, leading to significant errors in medical diagnosis and treatment. To ensure reliability, medical images should be annotated by experts like oncologists for effective model training. We propose PrefPaint, an approach that incorporates human feedback into the training process of Stable Diffusion Inpainting, bypassing the need for computationally expensive reward models. In addition, we develop a web-based interface streamlines training, fine-tuning, and inference. This interactive interface provides a smooth and intuitive user experience, making it easier to offer feedback and manage the fine-tuning process. User study on various domains shows that PrefPaint outperforms existing methods, reducing visual inconsistencies and improving image rendering, particularly in medical contexts, where our model generates more realistic polyps images.

Duy-Bao Bui、Hoang-Khang Nguyen、Trung-Nghia Le

医药卫生理论医学研究方法肿瘤学

Duy-Bao Bui,Hoang-Khang Nguyen,Trung-Nghia Le.PrefPaint: Enhancing Image Inpainting through Expert Human Feedback[EB/OL].(2025-06-27)[2025-07-17].https://arxiv.org/abs/2506.21834.点此复制

评论