Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Indoor Space Authentication by ISS-based Keypoint Extraction from 3D Point Clouds

Yuki Yamada, Daisuke Kotani, Kota Tsubouchi, Hidehito Gomi, Yasuo Okabe

TL;DR

Results show that keypoint-based sparse representation can make privacy-preserving, edge-deployable indoor space authentication practical, and opens a path toward device-independent authentication and account-recovery mechanisms that rely on users'physical environments.

Abstract

We propose ISS-RegAuth, a lightweight indoor space authentication framework that authenticates a user by comparing LiDAR captures of personal rooms. Prior work processes every point in the cloud, where planar surfaces such as walls and floors dominate similarity calculations, causing latency and potential privacy exposure. In contrast, ISS-RegAuth retains only 1-2\% of Intrinsic Shape Signatures (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 sparse representation can make privacy-preserving, edge-deployable indoor space authentication practical. As an early step, this work opens a path toward device-independent authentication and account-recovery mechanisms that rely on users' physical environments.

Indoor Space Authentication by ISS-based Keypoint Extraction from 3D Point Clouds

TL;DR

Results show that keypoint-based sparse representation can make privacy-preserving, edge-deployable indoor space authentication practical, and opens a path toward device-independent authentication and account-recovery mechanisms that rely on users'physical environments.

Abstract

We propose ISS-RegAuth, a lightweight indoor space authentication framework that authenticates a user by comparing LiDAR captures of personal rooms. Prior work processes every point in the cloud, where planar surfaces such as walls and floors dominate similarity calculations, causing latency and potential privacy exposure. In contrast, ISS-RegAuth retains only 1-2\% of Intrinsic Shape Signatures (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 sparse representation can make privacy-preserving, edge-deployable indoor space authentication practical. As an early step, this work opens a path toward device-independent authentication and account-recovery mechanisms that rely on users' physical environments.
Paper Structure (13 sections, 7 figures, 1 table)

This paper contains 13 sections, 7 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. ISS-RegAuth; Indoor Space Authentication by ISS-based Keypoint Extraction
  4. Authentication Procedure
  5. ISS-RegAuth Processing Pipeline
  6. Evaluation
  7. Experimental Setup
  8. Evaluation Metrics
  9. Results
  10. Discussion
  11. Threat Model and Privacy
  12. Applications to Account Recovery
  13. Conclusion and Future Work

Figures (7)

  • Figure 1: Indoor space authentication concept. Users enroll by scanning a private room and later re-scan it for verification.
  • Figure 2: Example pair of ARKitScenes captures from the same room used for enrollment (left) and probing (right).
  • Figure 3: ISS-RegAuth aligns only the salient keypoints (yellow/blue spheres) on top of the down-sampled clouds (green/red).
  • Figure 4: Similarity-score distributions for (top) the baseline suzuki2023 and (bottom) ISS-RegAuth (2%).
  • Figure 5: Example of enrollment and probe scans capturing partially different regions of the same room. ISS-RegAuth maintains consistent furniture-level correspondences despite limited overlap.
  • ...and 2 more figures