Image Realness Assessment and Localization with Multimodal Features
A reliable method of quantifying the perceptual realness of AI-generated images and identifying visually inconsistent regions is crucial for practical use of AI-generated images and for improving photorealism of generative AI via realness feedback during training. This paper introduces a framework that accomplishes both overall objective realness assessment and local inconsistency identification of AI-generated images using textual descriptions of visual inconsistencies generated by vision-language models trained on large datasets that serve as reliable substitutes for human annotations. Our results demonstrate that the proposed multimodal approach improves objective realness prediction performance and produces dense realness maps that effectively distinguish between realistic and unrealistic spatial regions.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
RAISE: Realness Assessment for Image Synthesis and Evaluation
The rapid advancement of generative AI has enabled the creation of highly photorealistic visual content, offering practical substitutes for real images and videos in scenarios where acquiring real data is difficult or ex…
Image GenerationCTSR: Controllable Fidelity-Realness Trade-off Distillation for Real-World Image Super Resolution
Real-world image super-resolution is a critical image processing task, where two key evaluation criteria are the fidelity to the original image and the visual realness of the generated results. Although existing methods …
Image Super-ResolutionSuper-ResolutionReal or Not Real, that is the Question
While generative adversarial networks (GAN) have been widely adopted in various topics, in this paper we generalize the standard GAN to a new perspective by treating realness as a random variable that can be estimated fr…
Detecting AI-Generated Forgeries via Iterative Manifold Deviation Amplification
The proliferation of highly realistic AI-generated images poses critical challenges for digital forensics, demanding precise pixel-level localization of manipulated regions. Existing methods predominantly learn discrimin…
GAN Prior based Null-Space Learning for Consistent Super-Resolution
Consistency and realness have always been the two critical issues of image super-resolution. While the realness has been dramatically improved with the use of GAN prior, the state-of-the-art methods still suffer inconsis…
Image Super-ResolutionSuper-Resolution