Fusion Transformer with Object Mask Guidance for Image Forgery Analysis

arXiv:2403.12229v1 Announce Type: new
Abstract: In this work, we introduce OMG-Fuser, a fusion transformer-based network designed to extract information from various forensic signals to enable robust image forgery detection and localization. Our approach can operate with an arbitrary number of forensic signals and leverages object information for their analysis -- unlike previous methods that rely on fusion schemes with few signals and often disregard image semantics. To this end, we design a forensic signal stream composed of a transformer guided …

abstract analysis arxiv cs.cv detection extract forgery fusion guidance image information localization network object robust transformer type work