PWPing Wang
Ping Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Ping Wang has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Honggu Liu
University of Science and Technology of China, Hefei, China
1 shared publication - Kunlin Liu
USTC
1 shared publication - Nenghai Yu
University of Science and Technology of China, Hefei, China
1 shared publication - Weiming Zhang
University of Science and Technology of China, Hefei, China
1 shared publication - Wenbo Zhou
School of Cyber Science and Technology, University of Science and Technology of China, China
1 shared publication - Yanhao Ge
Tencent Youtu, Shanghai 200233, China
1 shared publication
Latest Publications
- Open Access
- 22 November 2021
- Published by MDPI AG in Future Internet
- Vol. 13 (11) , 298
Face Swapping Consistency Transfer with Neural Identity Carrier
Deepfake aims to swap a face of an image with someone else’s likeness in a reasonable manner. Existing methods usually perform deepfake frame by frame, thus ignoring video consistency and producing incoherent results. To address such a problem, we propose a novel framework Neural Identity Carrier (NICe), which learns identity transformation from an arbitrary face-swapping proxy via a U-. By modeling the incoherence between frames as noise, NICe naturally suppresses its disturbance and preserves primary identity information. Concretely, NICe inputs the original frame and learns transformation supervised by swapped pseudo labels. As the temporal incoherence has an uncertain or stochastic pattern, NICe can filter out such outliers and well maintain the target content by uncertainty prediction. With the predicted temporally stable appearance, NICe enhances its details by constraining 3D geometry consistency, making NICe learn fine-grained facial structure across the poses. In this way, NICe guarantees the temporal stableness of deepfake approaches and predicts detailed results against over-smoothness. Extensive experiments on benchmarks demonstrate that NICe significantly improves the quality of existing deepfake methods on video-level. Besides, data generated by our methods can benefit video-level deepfake detection methods.- 22 November 2021
- Published by MDPI AG in Future Internet
- Vol. 13 (11) , 298
Open AccessFace Swapping Consistency Transfer with Neural Identity Carrier
Deepfake aims to swap a face of an image with someone else’s likeness in a reasonable manner. Existing methods usually perform deepfake frame by frame, thus ignoring video consistency and producing incoherent results. To address such a problem, we propose a novel framework Neural Identity Carrier (NICe), which learns identity transformation from an arbitrary face-swapping proxy via a U-. By modeling the incoherence between frames as noise, NICe naturally suppresses its disturbance and preserves primary identity information. Concretely, NICe inputs the original frame and learns transformation supervised by swapped pseudo labels. As the temporal incoherence has an uncertain or stochastic pattern, NICe can filter out such outliers and well maintain the target content by uncertainty prediction. With the predicted temporally stable appearance, NICe enhances its details by constraining 3D geometry consistency, making NICe learn fine-grained facial structure across the poses. In this way, NICe guarantees the temporal stableness of deepfake approaches and predicts detailed results against over-smoothness. Extensive experiments on benchmarks demonstrate that NICe significantly improves the quality of existing deepfake methods on video-level. Besides, data generated by our methods can benefit video-level deepfake detection methods.