期刊
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
卷 -, 期 -, 页码 2928-2938出版社
IEEE COMPUTER SOC
DOI: 10.1109/CVPR46437.2021.00295
关键词
-
资金
- National Key Research & Development Program [2020AAA0140002]
- Chinese National Natural Science Foundation [61806196, 61876178, 61976229, 61872367, 61961160704]
This paper proposes a method based on decomposition to detect digital face manipulation, utilizing facial details to uncover hidden forgery details. By decomposing face images into different elements such as 3D shape, textures, etc., subtle forgery patterns can be better detected. Experimental results show that our method achieves state-of-the-art performance in detecting subtle forgery patterns.
Detecting digital face manipulation has attracted extensive attention due to fake media's potential harms to the public. However, recent advances have been able to reduce the forgery signals to a low magnitude. Decomposition, which reversibly decomposes an image into several constituent elements, is a promising way to highlight the hidden forgery details. In this paper, we consider a face image as the production of the intervention of the underlying 3D geometry and the lighting environment, and decompose it in a computer graphics view. Specifically, by disentangling the face image into 3D shape, common texture, identity texture, ambient light, and direct light, we find the devil lies in the direct light and the identity texture. Based on this observation, we propose to utilize facial detail, which is the combination of direct light and identity texture, as the clue to detect the subtle forgery patterns. Besides, we highlight the manipulated region with a supervised attention mechanism and introduce a two-stream structure to exploit both face image and facial detail together as a multi-modality task. Extensive experiments indicate the effectiveness of the extra features extracted from the facial detail, and our method achieves the state-of-the-art performance.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据