Summary
Advances in photo editing and manipulation tools have made it significantly easier to create fake imagery. Learning to detect such manipulations, however, remains a challenging problem due to the lack of sufficient amounts of manipulated training data. In this paper, we propose a learning algorithm for detecting visual image manipulations that are trained only using a large dataset of real photographs. The algorithm uses the automatically recorded photo EXIF metadata as the supervisory signal for training a model to determine whether an image is self-consistent — that is, whether its content could have been produced by a single imaging pipeline. We apply this self-consistency model to the task of detecting and localizing image splices. The proposed method obtains state-of-the-art performance on several image forensics benchmarks, despite never seeing any manipulated images at training. That said, it is merely a step in the long quest for a truly general purpose visual forensics tool.
ECCV2018 #FUN
URL: https://arxiv.org/pdf/1805.04096.pdf Keyword: inpainting, meta data, metric learning Interest: 3 Code: https://minyoungg.github.io/selfconsistency/ Video: https://www.youtube.com/watch?time_continue=173&v=lmOejdhSio0
Summary Advances in photo editing and manipulation tools have made it significantly easier to create fake imagery. Learning to detect such manipulations, however, remains a challenging problem due to the lack of sufficient amounts of manipulated training data. In this paper, we propose a learning algorithm for detecting visual image manipulations that are trained only using a large dataset of real photographs. The algorithm uses the automatically recorded photo EXIF metadata as the supervisory signal for training a model to determine whether an image is self-consistent — that is, whether its content could have been produced by a single imaging pipeline. We apply this self-consistency model to the task of detecting and localizing image splices. The proposed method obtains state-of-the-art performance on several image forensics benchmarks, despite never seeing any manipulated images at training. That said, it is merely a step in the long quest for a truly general purpose visual forensics tool.