RelayFormer: A Unified Local-Global Attention Framework for Scalable Image and Video Manipulation Localization
Researchers have introduced RelayFormer, a novel framework designed to improve the localization of manipulated regions in images and videos. This unified approach addresses challenges related to resolution diversity and the separate handling of image and video data by existing methods. RelayFormer utilizes Global Local Relay (GLR) tokens and a relay-based attention mechanism to efficiently exchange contextual information while preserving fine-grained manipulation artifacts. AI
IMPACT Introduces a unified approach for visual manipulation localization, potentially improving efficiency and accuracy in detecting altered media.