Publications
OTHERS (INTERNATIONAL) Indoor Space Authentication by ISS-based Keypoint Extraction from 3D Point Clouds
Yuki Yamada (Kyoto University), Daisuke Kotani (Kyoto University), Kota Tsubouchi, Hidehito Gomi, Yasuo Okabe (Kyoto Unversity)
The 24th International Conference on Pervasive Computing and Communications (PerCom 2026)
March 17, 2026
We propose ISS-RegAuth, a lightweight indoor space authentication framework that verifies a user’s identity by comparing LiDAR captures of personal rooms. Unlike prior work that processes every point in the cloud—causing latency and privacy leakage—ISS-RegAuth retains only 1–2 % of Intrinsic Shape Signature (ISS) keypoints, computes their Fast Point Feature Histograms, and performs RANSAC and ICP on this sparse set. On 100 ARKitScenes pairs, this approach reduces the equal-error rate from 0.02 to 0.00, cuts processing time by 20 %, and lowers transmitted data to 2.2 % of the original. These results show that keypoint-based abstraction can make privacy-preserving, edge-deployable indoor space authentication practical. As an early step, this work opens a path toward device-free multi-factor and account-recovery mechanisms that rely on users’ physical environments rather than passwords or biometrics.