Point Cloud Classification

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

2 leaderboard tables shown for this task, 2 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

2 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

2 subtasks in the archive's task tree.

Most implemented papers archive 2025-07-28

30 shown of 138 papers with code (265 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Dynamic Graph CNN for Learning on Point Clouds
  24 Jan 2018 21 repositories listed Syntology ran 16 of 44 samples · 28 unverified · 31 pointer-only (licence)
  Point clouds provide a flexible geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices.
• PCT: Point cloud transformer
  17 Dec 2020 11 repositories listed Syntology ran 2 of 2 samples · 0 unverified
  It is inherently permutation invariant for processing a sequence of points, making it well-suited for point cloud learning.
• Beyond Self-attention: External Attention using Two Linear Layers for Visual Tasks
  5 May 2021 7 repositories listed
  Attention mechanisms, especially self-attention, have played an increasingly important role in deep feature representation for visual tasks.
• Deep Sets
  10 Mar 2017 7 repositories listed Syntology ran 9 of 12 samples · 3 unverified · 9 pointer-only (licence)
  Our main theorem characterizes the permutation invariant functions and provides a family of functions to which any permutation invariant objective function must belong.
• Benchmarking and Analyzing Point Cloud Classification under Corruptions
  7 Feb 2022 4 repositories listed Syntology ran 6 of 13 samples · 7 unverified
  3D perception, especially point cloud classification, has achieved substantial progress.
• Relation-Shape Convolutional Neural Network for Point Cloud Analysis
  16 Apr 2019 4 repositories listed Syntology ran 3 of 5 samples · 2 unverified
  Specifically, the convolutional weight for local point set is forced to learn a high-level relation expression from predefined geometric priors, between a sampled point from this point set and the others.
• Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling
  29 Nov 2021 3 repositories listed Syntology ran 4 of 6 samples · 2 unverified
  Inspired by BERT, we devise a Masked Point Modeling (MPM) task to pre-train point cloud Transformers.
• Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline
  9 Jun 2021 3 repositories listed Syntology ran 4 of 12 samples · 8 unverified
  It also outperforms state-of-the-art methods on ScanObjectNN, a real-world point cloud benchmark, and demonstrates better cross-dataset generalization.
• Walk in the Cloud: Learning Curves for Point Clouds Shape Analysis
  4 May 2021 3 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  Discrete point cloud objects lack sufficient shape descriptors of 3D geometries.
• Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud
  20 Dec 2020 3 repositories listed
  GDANet introduces Geometry-Disentangle Module to dynamically disentangle point clouds into the contour and flat part of 3D objects, respectively denoted by sharp and gentle variation components.
• Spherical Kernel for Efficient Graph Convolution on 3D Point Clouds
  20 Sep 2019 3 repositories listed Syntology ran 1 of 11 samples · 10 unverified
  We propose a spherical kernel for efficient graph convolution of 3D point clouds.
• Revisiting Point Cloud Classification: A New Benchmark Dataset and Classification Model on Real-World Data
  13 Aug 2019 3 repositories listed Syntology ran 2 of 6 samples · 4 unverified
  From our comprehensive benchmark, we show that our dataset poses great challenges to existing point cloud classification techniques as objects from real-world scans are often cluttered with background and/or are partial…
• PointHop: An Explainable Machine Learning Method for Point Cloud Classification
  30 Jul 2019 3 repositories listed
  In the attribute building stage, we address the problem of unordered point cloud data using a space partitioning procedure and developing a robust descriptor that characterizes the relationship between a point and its…
• 3D Point Cloud Classification and Segmentation using 3D Modified Fisher Vector Representation for Convolutional Neural Networks
  22 Nov 2017 3 repositories listed
  The point cloud is gaining prominence as a method for representing 3D shapes, but its irregular format poses a challenge for deep learning methods.
• FRACTAL: An Ultra-Large-Scale Aerial Lidar Dataset for 3D Semantic Segmentation of Diverse Landscapes
  7 May 2024 2 repositories listed
  To bridge this data gap, we introduce the FRench ALS Clouds from TArgeted Landscapes (FRACTAL) dataset: an ultra-large-scale aerial Lidar dataset made of 100, 000 dense point clouds with high quality labels for 7…
• Frozen Transformers in Language Models Are Effective Visual Encoder Layers
  19 Oct 2023 2 repositories listed Syntology ran 8 of 16 samples · 8 unverified
  This paper reveals that large language models (LLMs), despite being trained solely on textual data, are surprisingly strong encoders for purely visual tasks in the absence of language.
• Differentiable Euler Characteristic Transforms for Shape Classification
  11 Oct 2023 2 repositories listed Syntology ran 12 of 22 samples · 10 unverified
  The Euler Characteristic Transform (ECT) has proven to be a powerful representation, combining geometrical and topological characteristics of shapes and graphs.
• Robustifying Point Cloud Networks by Refocusing
  10 Aug 2023 2 repositories listed Syntology ran 15 of 22 samples · 7 unverified · 22 pointer-only (licence)
  In this study, we develop a general mechanism to increase neural network robustness based on focus analysis.
• SUG: Single-dataset Unified Generalization for 3D Point Cloud Classification
  16 May 2023 2 repositories listed
  In this paper, different from previous 2D DG works, we focus on the 3D DG problem and propose a Single-dataset Unified Generalization (SUG) framework that only leverages a single source dataset to alleviate the…
• Point Transformer V2: Grouped Vector Attention and Partition-based Pooling
  11 Oct 2022 2 repositories listed
  In this work, we analyze the limitations of the Point Transformer and propose our powerful and efficient Point Transformer V2 model with novel designs that overcome the limitations of previous work.
• Visualizing Global Explanations of Point Cloud DNNs
  17 Mar 2022 2 repositories listed
  In the field of autonomous driving and robotics, point clouds are showing their excellent real-time performance as raw data from most of the mainstream 3D sensors.
• LPF-Defense: 3D Adversarial Defense based on Frequency Analysis
  23 Feb 2022 2 repositories listed
  Although 3D point cloud classification has recently been widely deployed in different application scenarios, it is still very vulnerable to adversarial attacks.
• PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds
  26 Mar 2021 2 repositories listed Syntology ran 4 of 5 samples · 1 unverified
  The key of PAConv is to construct the convolution kernel by dynamically assembling basic weight matrices stored in Weight Bank, where the coefficients of these weight matrices are self-adaptively learned from point…
• PointCutMix: Regularization Strategy for Point Cloud Classification
  5 Jan 2021 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified
  As 3D point cloud analysis has received increasing attention, the insufficient scale of point cloud datasets and the weak generalization ability of networks become prominent.
• Revisiting Point Cloud Classification with a Simple and Effective Baseline
  1 Jan 2021 2 repositories listed
  It also outperforms state-of-the-art methods on ScanObjectNN, a real-world point cloud benchmark, and demonstrates better cross-dataset generalization.
• PointAugment: an Auto-Augmentation Framework for Point Cloud Classification
  25 Feb 2020 2 repositories listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)
  We present PointAugment, a new auto-augmentation framework that automatically optimizes and augments point cloud samples to enrich the data diversity when we train a classification network.
• PointHop++: A Lightweight Learning Model on Point Sets for 3D Classification
  9 Feb 2020 2 repositories listed
  The PointHop method was recently proposed by Zhang et al.
• Geometric Back-projection Network for Point Cloud Classification
  28 Nov 2019 2 repositories listed
  As the basic task of point cloud analysis, classification is fundamental but always challenging.
• Adversarial shape perturbations on 3D point clouds
  16 Aug 2019 2 repositories listed
  The importance of training robust neural network grows as 3D data is increasingly utilized in deep learning for vision tasks in robotics, drone control, and autonomous driving.
• Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
  10 Apr 2017 2 repositories listed Syntology ran 0 of 2 samples · 2 unverified
  A number of problems can be formulated as prediction on graph-structured data.

Syntology lines on 17 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.