Deep Image Comparator: Learning to Visualize Editorial Change
Authors:
- 1 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 972-980
Abstract
We present a novel architecture for comparing a pair of images to identify image regions that have been subjected to editorial manipulation. We first describe a robust near-duplicate search, for matching a potentially manipulated image circulating online to an image within a trusted database of originals. We then describe a novel architecture for comparing that image pair, to localize regions that have been manipulated to differ from the retrieved original. The localization ignores discrepancies due to benign image transformations that commonly occur during online redistribution. These include artifacts due to noise and recompression degradation, as well as out-of-place transformations due to image padding, warping, and changes in size and shape. Robustness towards out-of-place transformations is achieved via the end-to-end training of a differentiable warping module within the comparator architecture. We demonstrate effective retrieval and comparison of benign transformed and manipulated images, over a dataset of millions of photographs.Keywords
This publication has 17 references indexed in Scilit:
- In Ictu Oculi: Exposing AI Created Fake Videos by Detecting Eye Blinking2018
- ARCHANGEL2018
- Self-Supervised Feature Learning by Learning to Spot Artifacts2018
- HashNet: Deep Learning to Hash by Continuation2017
- Deep Residual Learning for Image Recognition2016
- Deep Supervised Hashing for Fast Image Retrieval2016
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- ImageNet: A large-scale hierarchical image database2009
- Dimensionality Reduction by Learning an Invariant Mapping2006
- MLESAC: A New Robust Estimator with Application to Estimating Image GeometryComputer Vision and Image Understanding, 2000