GUARD: Geometric Uncertainty-Aware Point Cloud Denoising and Segmentation for Robotic Hard Disk Drive Disassembly

Researchers introduced GUARD, a geometric uncertainty-aware framework that performs point filtering and segmentation in a single forward pass for robotic hard disk drive (HDD) disassembly, improving PointNet++ segmentation mean intersection over union from 0.7739 to 0.8318 on 2,745 real HDD point clouds. GUARD combines a multi-scale geometric transformer with a multi-bandwidth random Fourier feature Gaussian Process to estimate per-point geometric uncertainty, and on manually annotated ScanNet samples its geometric uncertainty achieved a corrupted-point detection F1 score of 0.7931 versus 0.2212 for predictive entropy. The work, posted as arXiv:2610.09068v1, argues that distinguishing geometric reliability from semantic confidence matters for interpreting imperfect 3D measurements used in component identification and robotic handling.

arXiv:2610.09068v1 Announce Type: new Abstract: Reliable robotic disassembly requires part-level representations that distinguish genuine component geometry from scanning and reconstruction artifacts. In point clouds of hard disk drives HDDs , structured ghost artifacts can resemble valid components locally while remaining inconsistent with the overall geometry, allowing erroneous measurements to receive plausible semantic labels. This creates an engineering information problem: semantic prediction confidence alone does not establish whether the underlying geometry is reliable. We propose \textbf{GUARD}, a geometric uncertainty-aware framework that performs point filtering and segmentation within a single forward pass by modeling the reliability of learned geometric representations. GUARD combines a multi-scale geometric transformer with a multi-bandwidth random Fourier feature Gaussian Process to estimate per-point geometric uncertainty, complemented by predictive entropy to suppress unreliable measurements while preserving informative structures. Evaluation on 2,745 real HDD point clouds shows that GUARD improves PointNet++ segmentation mean intersection over union from 0.7739 to 0.8318. Additional experiments on ShapeNetPart and ScanNet examine robustness across corruption types, point-cloud domains, and segmentation backbones. On manually annotated ScanNet samples, geometric uncertainty achieves a corrupted-point detection F1 score of 0.7931, compared with 0.2212 for predictive entropy. The results demonstrate the value of distinguishing geometric reliability from semantic confidence and reveal a tradeoff between artifact suppression and preservation of informative structures. GUARD contributes a reliability-aware approach to interpreting imperfect 3D measurements for component identification and subsequent robotic handling. Project website: https://001-wang.github.io/GUARD Point denoiser/.