paper-with-me

Papers

Robust 3D Point Clouds Classification based on Declarative Defenders

2024-10-13 · Kaidong Li, Tianxiao Zhang, Cuncong Zhong, Ziming Zhang, Guanghui Wang

3D point cloud classification requires distinct models from 2D image classification due to the divergent characteristics of the respective input data. While 3D point clouds are unstructured and sparse, 2D images are structured and dense. Bridging the domain gap between these two data types is a non-trivial challenge to enable model interchangeability. Recent research using Lattice Point Classifier (LPC) highlights the feasibility of cross-domain applicability. However, the lattice projection operation in LPC generates 2D images with disconnected projected pixels. In this paper, we explore three distinct algorithms for mapping 3D point clouds into 2D images. Through extensive experiments, we thoroughly examine and analyze their performance and defense mechanisms. Leveraging current large foundation models, we scrutinize the feature disparities between regular 2D images and projected 2D images. The proposed approaches demonstrate superior accuracy and robustness against adversarial attacks. The generative model-based mapping algorithms yield regular 2D images, further minimizing the domain gap from regular 2D classification tasks. The source code is available at https://github.com/KaidongLi/pytorch-LatticePointClassifier.git.

📄 PDF Abstract BibTeX arXiv:2410.09691

Code (1)

KaidongLi/pytorch-LatticePointClassifier 공식 구현 pytorch

Tasks

3D Point Cloud Classificationimage-classificationImage ClassificationPoint Cloud Classification

Similar Papers 제목 키워드 기반

Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks with Implicit Gradients

2022-03-29 · CVPR 2022 1 · Kaidong Li, Ziming Zhang, Cuncong Zhong, Guanghui Wang

Deep neural networks for 3D point cloud classification, such as PointNet, have been demonstrated to be vulnerable to adversarial attacks. Current adversarial defenders often learn to denoise the (attacked) point clouds b…

3D Point Cloud ClassificationBilevel OptimizationClassificationPoint Cloud Classification

MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization

2021-01-17 · CVPR 2021 1 · Jiahui Huang, He Wang, Tolga Birdal, Minhyuk Sung 외

We present MultiBodySync, a novel, end-to-end trainable multi-body motion segmentation and rigid registration framework for multiple input 3D point clouds. The two non-trivial challenges posed by this multi-scan multibod…

Motion EstimationMotion SegmentationSegmentation

Deep Declarative Networks: A New Hope

2019-09-11 · Stephen Gould, Richard Hartley, Dylan Campbell

We explore a new class of end-to-end learnable models wherein data processing nodes (or network layers) are defined in terms of desired behavior rather than an explicit forward function. Specifically, the forward functio…

Point Cloud Classification

PWAVEP: Purifying Imperceptible Adversarial Perturbations in 3D Point Clouds via Spectral Graph Wavelets

2026-02-03 · Haoran Li, Renyang Liu, Hongjia Liu, Chen Wang 외 arxiv

Recent progress in adversarial attacks on 3D point clouds, particularly in achieving spatial imperceptibility and high attack performance, presents significant challenges for defenders. Current defensive approaches remai…

Point Clouds

Towards a Multi-Agent Simulation of Cyber-attackers and Cyber-defenders Battles

2025-06-05 · Julien Soulé, Jean-Paul Jamont, Michel Occello, Paul Théron 외

As cyber-attacks show to be more and more complex and coordinated, cyber-defenders strategy through multi-agent approaches could be key to tackle against cyber-attacks as close as entry points in a networked system. This…