Assessing Image Inpainting via Re-Inpainting Self-Consistency Evaluation
Image inpainting, the task of reconstructing missing segments in corrupted images using available data, faces challenges in ensuring consistency and fidelity, especially under information-scarce conditions. Traditional evaluation methods, heavily dependent on the existence of unmasked reference images, inherently favor certain inpainting outcomes, introducing biases. Addressing this issue, we introduce an innovative evaluation paradigm that utilizes a self-supervised metric based on multiple re-inpainting passes. This approach, diverging from conventional reliance on direct comparisons in pixel or feature space with original images, emphasizes the principle of self-consistency to enable the exploration of various viable inpainting solutions, effectively reducing biases. Our extensive experiments across numerous benchmarks validate the alignment of our evaluation method with human judgment.
Code (0)
등록된 구현이 없습니다.
Tasks
Image InpaintingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Trans-Adapter: A Plug-and-Play Framework for Transparent Image Inpainting
RGBA images, with the additional alpha channel, are crucial for any application that needs blending, masking, or transparency effects, making them more versatile than standard RGB images. Nevertheless, existing image inp…
Image InpaintingImage MattingDeep Generative Model for Image Inpainting with Local Binary Pattern Learning and Spatial Attention
Deep learning (DL) has demonstrated its powerful capabilities in the field of image inpainting. The DL-based image inpainting approaches can produce visually plausible results, but often generate various unpleasant artif…
Image InpaintingDeep Stereo Video Inpainting
Stereo video inpainting aims to fill the missing regions on the left and right views of the stereo video with plausible content simultaneously. Compared with the single video inpainting that has achieved promising re…
Video InpaintingBoosted GAN with Semantically Interpretable Information for Image Inpainting
Image inpainting aims at restoring missing region of corrupted images, which has many applications such as image restoration and object removal. However, current GAN-based inpainting models fail to explicitly consider th…
AttributeImage InpaintingImage RestorationSegmentationMTADiffusion: Mask Text Alignment Diffusion Model for Object Inpainting
Advancements in generative models have enabled image inpainting models to generate content within specific regions of an image based on provided prompts and masks. However, existing inpainting methods often suffer from p…
Image Inpainting