Benchmarking and Analyzing Point Cloud Classification under Corruptions

• URL: http://arxiv.org/abs/2202.03377v1
• Date: Mon, 7 Feb 2022 17:50:21 GMT
• Title: Benchmarking and Analyzing Point Cloud Classification under Corruptions
• Authors: Jiawei Ren and Liang Pan and Ziwei Liu
• Abstract summary: We benchmark and analyze point cloud classification under corruptions. Based on the obtained observations, we propose several effective techniques to enhance point cloud robustness.
• Score: 33.252032774949356
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D perception, especially point cloud classification, has achieved substantial progress. However, in real-world deployment, point cloud corruptions are inevitable due to the scene complexity, sensor inaccuracy, and processing imprecision. In this work, we aim to rigorously benchmark and analyze point cloud classification under corruptions. To conduct a systematic investigation, we first provide a taxonomy of common 3D corruptions and identify the atomic corruptions. Then, we perform a comprehensive evaluation on a wide range of representative point cloud models to understand their robustness and generalizability. Our benchmark results show that although point cloud classification performance improves over time, the state-of-the-art methods are on the verge of being less robust. Based on the obtained observations, we propose several effective techniques to enhance point cloud classifier robustness. We hope our comprehensive benchmark, in-depth analysis, and proposed techniques could spark future research in robust 3D perception.

Related papers

• Deep Learning for 3D Point Cloud Enhancement: A Survey [7.482216242644069]
  This paper presents a comprehensive survey for deep-learning-based point cloud enhancement methods. It covers three main perspectives for point cloud enhancement, i.e., denoising to achieve clean data, completion to recover unseen data, and upsampling to obtain dense data. Our survey presents a new taxonomy for recent state-of-the-art methods and systematic experimental results on standard benchmarks.
  arXiv  Detail & Related papers  (2024-10-30T15:07:06Z)
• Deep Learning-based 3D Point Cloud Classification: A Systematic Survey and Outlook [12.014972829130764]
  This paper introduces point cloud acquisition, characteristics, and challenges. We review 3D data representations, storage formats, and commonly used datasets for point cloud classification.
  arXiv  Detail & Related papers  (2023-11-05T09:28:43Z)
• Risk-optimized Outlier Removal for Robust 3D Point Cloud Classification [54.286437930350445]
  This paper highlights the challenges of point cloud classification posed by various forms of noise. We introduce an innovative point outlier cleansing method that harnesses the power of downstream classification models. Our proposed technique not only robustly filters diverse point cloud outliers but also consistently and significantly enhances existing robust methods for point cloud classification.
  arXiv  Detail & Related papers  (2023-07-20T13:47:30Z)
• PointCA: Evaluating the Robustness of 3D Point Cloud Completion Models Against Adversarial Examples [63.84378007819262]
  We propose PointCA, the first adversarial attack against 3D point cloud completion models. PointCA can generate adversarial point clouds that maintain high similarity with the original ones. We show that PointCA can cause a performance degradation from 77.9% to 16.7%, with the structure chamfer distance kept below 0.01.
  arXiv  Detail & Related papers  (2022-11-22T14:15:41Z)
• Common Corruption Robustness of Point Cloud Detectors: Benchmark and Enhancement [17.228852716121885]
  Object detection through LiDAR-based point cloud has recently been important in autonomous driving. There is a lack of a large-scale dataset covering diverse scenes and realistic corruption types with different severities. We propose the physical-aware simulation methods to generate degraded point clouds under different real-world common corruptions.
  arXiv  Detail & Related papers  (2022-10-12T03:23:35Z)
• Blind Quality Assessment of 3D Dense Point Clouds with Structure Guided Resampling [71.68672977990403]
  We propose an objective point cloud quality index with Structure Guided Resampling (SGR) to automatically evaluate the perceptually visual quality of 3D dense point clouds. The proposed SGR is a general-purpose blind quality assessment method without the assistance of any reference information.
  arXiv  Detail & Related papers  (2022-08-31T02:42:55Z)
• PointAttN: You Only Need Attention for Point Cloud Completion [89.88766317412052]
  Point cloud completion refers to completing 3D shapes from partial 3D point clouds. We propose a novel neural network for processing point cloud in a per-point manner to eliminate kNNs. The proposed framework, namely PointAttN, is simple, neat and effective, which can precisely capture the structural information of 3D shapes.
  arXiv  Detail & Related papers  (2022-03-16T09:20:01Z)
• Shape-invariant 3D Adversarial Point Clouds [111.72163188681807]
  Adversary and invisibility are two fundamental but conflict characters of adversarial perturbations. Previous adversarial attacks on 3D point cloud recognition have often been criticized for their noticeable point outliers. We propose a novel Point-Cloud Sensitivity Map to boost both the efficiency and imperceptibility of point perturbations.
  arXiv  Detail & Related papers  (2022-03-08T12:21:35Z)
• Unsupervised Point Cloud Representation Learning with Deep Neural Networks: A Survey [104.71816962689296]
  Unsupervised point cloud representation learning has attracted increasing attention due to the constraint in large-scale point cloud labelling. This paper provides a comprehensive review of unsupervised point cloud representation learning using deep neural networks.
  arXiv  Detail & Related papers  (2022-02-28T07:46:05Z)
• Benchmarking Robustness of 3D Point Cloud Recognition Against Common Corruptions [38.89370166717221]
  We present ModelNet40-C, the first comprehensive benchmark on 3D point cloud corruption robustness. Our evaluation shows a significant gap between the performances on ModelNet40 and ModelNet40-C for state-of-the-art (SOTA) models. We unveil that Transformer-based architectures with proper training recipes achieve the strongest robustness.
  arXiv  Detail & Related papers  (2022-01-28T18:01:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.