GUARD: Geometric Uncertainty-Aware Point Cloud Denoising and Segmentation for Robotic Hard Disk Drive Disassembly
Quick Answer
GUARD is a novel framework for point cloud denoising and segmentation, enhancing geometric reliability in robotic disassembly of hard disk drives.
Quick Take
It improves segmentation performance from 0.7739 to 0.8318 in PointNet++ and achieves a corrupted-point detection F1 score of 0.7931, outperforming predictive entropy significantly.
Key Points
- GUARD combines a geometric transformer with a Gaussian Process for uncertainty estimation.
- Evaluated on 2,745 real HDD point clouds, showing significant performance improvements.
- Achieves a mean intersection over union of 0.8318 in segmentation tasks.
- Demonstrates a tradeoff between artifact suppression and structure preservation.
- Robust across various corruption types and point-cloud domains.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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: this https URL.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO) |
| Cite as: | arXiv:2610.09068 [cs.CV] |
| (or arXiv:2610.09068v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09068 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xiao Liang [view email]
[v1]
Tue, 6 Oct 2026 20:15:34 UTC (1,894 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.