REVEAL -- Reasoning and Evaluation of Visual Evidence through Aligned Language
This addresses the challenge of robust image forgery detection with reasoning and localization for applications in media verification and security, though it is incremental as it builds on existing vision-language models.
The paper tackles the problem of detecting and interpreting visual forgeries by framing it as a prompt-driven visual reasoning task, achieving generalization across domains like Photoshop, DeepFake, and AIGC editing through the REVEAL framework.
The rapid advancement of generative models has intensified the challenge of detecting and interpreting visual forgeries, necessitating robust frameworks for image forgery detection while providing reasoning as well as localization. While existing works approach this problem using supervised training for specific manipulation or anomaly detection in the embedding space, generalization across domains remains a challenge. We frame this problem of forgery detection as a prompt-driven visual reasoning task, leveraging the semantic alignment capabilities of large vision-language models. We propose a framework, `REVEAL` (Reasoning and Evaluation of Visual Evidence through Aligned Language), that incorporates generalized guidelines. We propose two tangential approaches - (1) Holistic Scene-level Evaluation that relies on the physics, semantics, perspective, and realism of the image as a whole and (2) Region-wise anomaly detection that splits the image into multiple regions and analyzes each of them. We conduct experiments over datasets from different domains (Photoshop, DeepFake and AIGC editing). We compare the Vision Language Models against competitive baselines and analyze the reasoning provided by them.