SAFIRE: Segment Any Forged Image Region

TL;DR

SAFIRE introduces a novel point prompting method for forgery localization, enabling partitioning of images into multiple source regions and improving stability and performance over traditional binary segmentation approaches.

Contribution

It presents a new source-based segmentation approach using point prompts, allowing multiple source regions and enhancing forgery detection stability.

Findings

Achieves superior performance in forgery localization tasks.

Enables partitioning images into multiple source regions.

Focuses on uniform source region characteristics.

Abstract

Most techniques approach the problem of image forgery localization as a binary segmentation task, training neural networks to label original areas as 0 and forged areas as 1. In contrast, we tackle this issue from a more fundamental perspective by partitioning images according to their originating sources. To this end, we propose Segment Any Forged Image Region (SAFIRE), which solves forgery localization using point prompting. Each point on an image is used to segment the source region containing itself. This allows us to partition images into multiple source regions, a capability achieved for the first time. Additionally, rather than memorizing certain forgery traces, SAFIRE naturally focuses on uniform characteristics within each source region. This approach leads to more stable and effective learning, achieving superior performance in both the new task and the traditional binary forgery localization.