IVCVMar 16, 2020

Camera Trace Erasing

arXiv:2003.06951v123 citationsHas Code
AI Analysis

This addresses a low-level vision problem for digital imaging security, but it appears incremental as it builds on existing anti-forensic methods.

The paper tackles the problem of erasing camera trace noise to undermine forensic methods that rely on it for image origin identification, proposing Siamese Trace Erasing (SiamTE) which outperforms existing anti-forensic methods in three tasks.

Camera trace is a unique noise produced in digital imaging process. Most existing forensic methods analyze camera trace to identify image origins. In this paper, we address a new low-level vision problem, camera trace erasing, to reveal the weakness of trace-based forensic methods. A comprehensive investigation on existing anti-forensic methods reveals that it is non-trivial to effectively erase camera trace while avoiding the destruction of content signal. To reconcile these two demands, we propose Siamese Trace Erasing (SiamTE), in which a novel hybrid loss is designed on the basis of Siamese architecture for network training. Specifically, we propose embedded similarity, truncated fidelity, and cross identity to form the hybrid loss. Compared with existing anti-forensic methods, SiamTE has a clear advantage for camera trace erasing, which is demonstrated in three representative tasks. Code and dataset are available at https://github.com/ngchc/CameraTE.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes