| Paper ID | B-2-3.7 |
| Paper Title |
Color Transfer to Anonymized Gait Images While Maintaining Anonymization |
| Authors |
Ngoc-Dung T. Tieu, Junichi Yamagishi, Isao Echizen, National Institute of Informatics,, Japan |
| Session |
B-2-3: Deep Generative Models for Media Clones and Its Detection |
| Time | Wednesday, 09 December, 17:15 - 19:15 |
| Presentation Time: | Wednesday, 09 December, 18:45 - 19:00 Check your Time Zone |
|
All times are in New Zealand Time (UTC +13) |
| Topic |
Multimedia Security and Forensics (MSF): Special Session: Deep Generative Models for Media Clones and Its Detection |
| Abstract |
Gait anonymization helps prevent the identification of people by gait recognition systems using videos uploaded to social media. Gait anonymization approach is to first modify the silhouette of the gait sequence and then transfer the colors of the skin, hair, clothing, etc. in the original gait images to the modified gait images to produce a final RGB anonymized gait image sequence. Since users care about the quality of the generated videos as they want to share them with family and friends in addition to caring about privacy, the generated videos should contain color images that are sharp and finely textured. Existing anonymization models are unable to produce such images. To overcome this problem, we propose transferring the colors without using ground truth and without extracting the colors in the original gait images. The overlapping region between the two gaits is first located, and the colors in that region in the original images are transferred to the modified images. The colors in the remaining region are interpolated from the color in the overlapping region, so the colors in the overlapping and non-overlapping regions are coherent. Experiments demonstrated that the proposed model is more effective than existing models with no anonymization reduction. |