• Home
  • Search
  • 3DVerifier: efficient robustness verification for 3D point cloud models
  • Cite Icon14
  • https://doi.org/10.1007/s10994-022-06235-3Copy DOI Icon

3DVerifier: efficient robustness verification for 3D point cloud models

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

3D point cloud models are widely applied in safety-critical scenes, which delivers an urgent need to obtain more solid proofs to verify the robustness of models. Existing verification method for point cloud model is time-expensive and computationally unattainable on large networks. Additionally, they cannot handle the complete PointNet model with joint alignment network that contains multiplication layers, which effectively boosts the performance of 3D models. This motivates us to design a more efficient and general framework to verify various architectures of point cloud models. The key challenges in verifying the large-scale complete PointNet models are addressed as dealing with the cross-non-linearity operations in the multiplication layers and the high computational complexity of high-dimensional point cloud inputs and added layers. Thus, we propose an efficient verification framework, 3DVerifier, to tackle both challenges by adopting a linear relaxation function to bound the multiplication layer and combining forward and backward propagation to compute the certified bounds of the outputs of the point cloud models. Our comprehensive experiments demonstrate that 3DVerifier outperforms existing verification algorithms for 3D models in terms of both efficiency and accuracy. Notably, our approach achieves an orders-of-magnitude improvement in verification efficiency for the large network, and the obtained certified bounds are also significantly tighter than the state-of-the-art verifiers. We release our tool 3DVerifier via https://github.com/TrustAI/3DVerifier for use by the community.

Similar Papers
  • Discussion
  • Citations7

Two-Dimensional LiDAR Sensor-Based Three-Dimensional Point Cloud Modeling Method for Identification of Anomalies inside Tube Structures for Future Hypersonic Transportation

  • Dec 17, 2020
  • Sensors (Basel, Switzerland)
  • Jongdae Baek
  • Conference Article
  • Citations2

Quality evaluation of point cloud model for interior structure of a common building

  • Jul 01, 2017
  • Gen Li +5
  • Conference Article
  • Citations7

Dense point-cloud creation using superresolution for a monocular 3D reconstruction system

  • May 01, 2012
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Yakov Diskin +1
  • Conference Article
  • Citations2

Adaptive noise suppression technique for dense 3D point cloud reconstructions from monocular vision

  • Oct 15, 2012
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • Yakov Diskin +1
  • Research Article
  • Citations22

GrainPointNet: A deep-learning framework for non-invasive sorghum panicle grain count phenotyping

  • Dec 21, 2023
  • Computers and Electronics in Agriculture
  • Chrisbin James +4
  • Research Article
  • Citations5

Learned 3D shape descriptors for classifying 3D point cloud models

  • Nov 22, 2016
  • Computer-Aided Design and Applications
  • Xiaojun Zhao +1
  • Conference Article

3D point cloud classification model based on local location information

  • Oct 20, 2022
  • Teng Chen +5
  • Conference Article

Theoretical Research on Adjacent Multi-station Point Cloud Data Precision Combination in 3D Laser Scanning

  • Dec 01, 2010
  • Tianzi Li +1
  • Research Article
  • Citations5

Three-dimensional modeling and defect quantification of existing concrete bridges based on photogrammetry and computer aided design

  • Mar 16, 2023
  • Ain Shams Engineering Journal
  • Saleh Abu Dabous +2
  • Conference Article
  • Citations2

Developing a Human-Cognition-Based Reverse Engineering Approach

  • Sep 03, 2020
  • Tashi +2
  • PDF
  • Research Article
  • Citations7

MULTI-SENSOR 3D RECORDING PIPELINE FOR THE DOCUMENTATION OF JAVANESE TEMPLES

  • Aug 23, 2019
  • The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
  • A Murtiyos +5
  • Conference Article
  • Citations5

Three-dimensional point-cloud room model for room acoustics simulations

  • Jan 01, 2013
  • Proceedings of meetings on acoustics
  • Milos Markovic +2
  • PDF
  • Research Article
  • Citations14

Harnessing Digital Twins for Agriculture 5.0: A Comparative Analysis of 3D Point Cloud Tools

  • Feb 20, 2024
  • Applied Sciences
  • Paula Catala-Roman +3
  • Research Article
  • Citations4

Real-Time Environmental Contour Construction Using 3D LiDAR and Image Recognition with Object Removal

  • Dec 01, 2024
  • Remote Sensing
  • Tzu-Jung Wu +2
  • Research Article
  • Citations3

Accurately Computing the Interacted Volume of Molecules over Their 3D Mesh Models.

  • Jul 04, 2024
  • Journal of chemical information and modeling
  • Fangting Li +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.