Exposing photo manipulation with inconsistent shadows

106 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

SafetyNet: Detecting and Rejecting Adversarial Examples Robustly (2017, background): “Current best methods to identify fake images require careful analysis of vanishing points [8], illumination angles [6], and shadows [11] (reviews in [8, 7]).”
MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detection (2021, unknown): “The differences are calculated by varied approaches, including media-format based compression artifacts [6], [7], physics-based lighting inconsistency [8], [9], statistical modeling [10], local noise estimation [11], etc.”
Media Forensics and DeepFakes: An Overview (2020, background): “for example shadows or illumination or perspective [3], [4], [5].”