CorrFill: Enhancing Faithfulness in Reference-based Inpainting with Correspondence Guidance in Diffusion Models
원문 초록
In the task of reference-based image inpainting, an additional reference image is provided to restore a damaged target image to its original state. The advancement of diffusion models, particularly Stable Diffusion, allows for simple formulations in this task. However, existing diffusion-based methods often lack explicit constraints on the correlation between the reference and damaged images, resulting in lower faithfulness to the reference images in the inpainting results. In this work, we propose CorrFill, a training-free module designed to enhance the awareness of geometric correlations between the reference and target images. This enhancement is achieved by guiding the inpainting process with correspondence constraints estimated during inpainting, utilizing attention masking in self-attention layers and an objective function to update the input tensor according to the constraints. Experimental results demonstrate that CorrFill significantly enhances the performance of multiple baseline diffusion-based methods, including state-of-the-art approaches, by emphasizing faithfulness to the reference images.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Unsupervised Raindrop Removal from a Single Image using Conditional Diffusion Models
Leveraging Depth Maps and Attention Mechanisms for Enhanced Image Inpainting
Visibility-Uncertainty-guided 3D Gaussian Inpainting via Scene Conceptional Learning
Autoregressive Image Generation with Randomized Parallel Decoding
VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control
Tackling Few-Shot Segmentation in Remote Sensing via Inpainting Diffusion Model
토론
이 논문과 연결된 포럼 글이 아직 없습니다.