Forbes: Face Obfuscation Rendering via Backpropagation Refinement Scheme
Abstract
A novel algorithm for face obfuscation, called Forbes, which aims to obfuscate facial appearance recognizable by humans but preserve the identity and attributes decipherable by machines, is proposed in this paper. Forbes first applies multiple obfuscating transformations with random parameters to an image to remove the identity information distinguishable by humans. Then, it optimizes the parameters to make the transformed image decipherable by machines based on the backpropagation refinement scheme. Finally, it renders an obfuscated image by applying the transformations with the optimized parameters. Experimental results on various datasets demonstrate that Forbes achieves both human indecipherability and machine decipherability excellently. The source codes are available at https://github.com/mcljtkim/Forbes.
Cite
Text
Kim et al. "Forbes: Face Obfuscation Rendering via Backpropagation Refinement Scheme." Proceedings of the European Conference on Computer Vision (ECCV), 2024. doi:10.1007/978-3-031-72890-7_4Markdown
[Kim et al. "Forbes: Face Obfuscation Rendering via Backpropagation Refinement Scheme." Proceedings of the European Conference on Computer Vision (ECCV), 2024.](https://mlanthology.org/eccv/2024/kim2024eccv-forbes/) doi:10.1007/978-3-031-72890-7_4BibTeX
@inproceedings{kim2024eccv-forbes,
title = {{Forbes: Face Obfuscation Rendering via Backpropagation Refinement Scheme}},
author = {Kim, Jintae and Yang, Seungwon and Jeong, Seong-Gyun and Kim, Chang-Su},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2024},
doi = {10.1007/978-3-031-72890-7_4},
url = {https://mlanthology.org/eccv/2024/kim2024eccv-forbes/}
}