Reproduce “Face De-Identification: A Domain-Centric Survey from Capture to Processing” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Hui Wei, Hao Yu, Guoying Zhao
The survey organizes face de-identification methods by when protection enters the imaging pipeline: before capture, during capture, or after an image is recorded. It reviews 112 methods and finds that privacy is reported across all three domains, while utility reporting ranges from 0% of physical methods to 100% of sensor methods. These are reporting rates, not comparable performance results.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.