Disharmony: Forensics using Reverse Lighting Harmonization
This addresses the need for improved forensic detection of manipulated images, particularly for identifying harmonized objects, which is an incremental advance in image forensics.
The paper tackles the problem of detecting edited or generated image regions by using harmonization data with a segmentation model, and demonstrates that this approach effectively identifies such edits, outperforming existing forensic networks.
Content generation and manipulation approaches based on deep learning methods have seen significant advancements, leading to an increased need for techniques to detect whether an image has been generated or edited. Another area of research focuses on the insertion and harmonization of objects within images. In this study, we explore the potential of using harmonization data in conjunction with a segmentation model to enhance the detection of edited image regions. These edits can be either manually crafted or generated using deep learning methods. Our findings demonstrate that this approach can effectively identify such edits. Existing forensic models often overlook the detection of harmonized objects in relation to the background, but our proposed Disharmony Network addresses this gap. By utilizing an aggregated dataset of harmonization techniques, our model outperforms existing forensic networks in identifying harmonized objects integrated into their backgrounds, and shows potential for detecting various forms of edits, including virtual try-on tasks.