SAFIRE uses point prompting and feature clustering to partition forged images into multiple source regions, and reports state-of-the-art results on both binary forgery localization and a new multi-source partitioning task.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
SAFIRE: Segment Any Forged Image Region
SAFIRE uses point prompting and feature clustering to partition forged images into multiple source regions, and reports state-of-the-art results on both binary forgery localization and a new multi-source partitioning task.