Browse State-of-the-Art › 3D Object Classification
3D Object Classification
47 papers with code · 4 benchmarks · 7 datasets archive 2025-07-28
3D Object Classification is the task of predicting the class of a 3D object point cloud. It is a voxel level prediction where each voxel is classified into a category. The popular benchmark for this task is the ModelNet dataset. The models for this task are usually evaluated with the Classification Accuracy metric.
Image: Sedaghat et al
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
4 leaderboard tables shown for this task, 4 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.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| ModelNet40 (7 rows) | Ours | Exploiting Inductive Bias in Transformer for Point Cloud... | code | — | Compare |
| ModelNet10 (4 rows) | PolyNet | PolyNet: Polynomial Neural Network for 3D Shape Recognition with... | code | — | Compare |
| 3R-Scan (2 rows) | SceneGraphFusion | SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D... | code | — | Compare |
| Remote Flash LiDAR Vehicles Dataset (1 row) | YOLO-X | Real-time object detection and tracking using flash LiDAR imagery | — | — | Compare |
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. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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
7 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.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 93 · with a code link: 47 · where Syntology ran a sample: 9 (6 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (9 of 93 tagged: 6 with a run with no instrument failure, 3 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 93 of 93, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
31 Aug 2023 3 repositories listedThe unprecedented advancements in Large Language Models (LLMs) have shown a profound impact on natural language processing but are yet to fully embrace the realm of 3D understanding.
-
22 Nov 2021 3 repositories listedMLP-Mixer has newly appeared as a new challenger against the realm of CNNs and transformer.
-
20 Dec 2020 3 repositories listedGDANet 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.
-
20 Sep 2019 3 repositories listed Syntology official (archive's flag): 2 ran · 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified (of 11 harvested samples)We propose a spherical kernel for efficient graph convolution of 3D point clouds.
-
13 Aug 2019 3 repositories listed Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 6 harvested samples) · 1 pointer-only (licence)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…
-
12 Dec 2023 2 repositories listedTo this end, we propose a more realistic and challenging scenario named open-pose 3D zero-shot classification, focusing on the recognition of 3D objects regardless of their orientation.
-
10 Oct 2023 2 repositories listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples)Scaling up representations for images or text has been extensively investigated in the past few years and has led to revolutions in learning vision and language.
-
27 Mar 2021 2 repositories listedScene graphs are a compact and explicit representation successfully used in a variety of 2D scene understanding tasks.
-
2 Nov 2020 2 repositories listed Syntology official (archive's flag): 1 ran · 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)In this work, we present Point Transformer, a deep neural network that operates directly on unordered and unstructured point sets.
-
27 Dec 2018 2 repositories listedIn this paper, we propose 3D point-capsule networks, an auto-encoder designed to process sparse 3D point clouds while preserving spatial arrangements of the input data.
-
10 Apr 2017 2 repositories listed Syntology official: not harvested · 0 ran · 2 unverified (of 2 harvested samples)A number of problems can be formulated as prediction on graph-structured data.
-
14 Oct 2024 1 repository listedKANs have been integrated into various deep learning architectures such as convolutional neural networks, graph neural networks, and transformers, with their performance evaluated.
-
16 Aug 2024 1 repository listedThese methods typically include an encoder accepting visible patches (normalized) and corresponding patch centers (position) as input, with the decoder accepting the output of the encoder and the centers (position) of…
-
13 Aug 2024 1 repository listedInspired by Geoffrey Hinton emphasis on generative modeling, To recognize shapes, first learn to generate them, we explore the use of 3D diffusion models for object classification.
-
2 May 2024 1 repository listedNotably, MiniGPT-3D gains an 8.
-
9 Mar 2024 1 repository listedThe proposed approach is a combination of the GRU and LSTM.
-
17 Nov 2023 1 repository listedHowever, a notable limitation of these approaches is that they do not fully utilize the multi-view attributes inherent in 3D point clouds, which is crucial for a deeper understanding of 3D structures.
-
13 Oct 2023 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample) · 1 pointer-only (licence)Inspired by recent C-MCR, this paper proposes Extending Multimodal Contrastive Representation (Ex-MCR), a training-efficient and paired-data-free method to flexibly learn unified contrastive representation space for…
-
8 Jun 2023 1 repository listedIn this study, we introduce a novel selfsupervised method called CrossMoCo, which learns the representations of unlabelled point cloud data in a multi-modal setup that also utilizes the 2D rendered images of the point…
-
27 Apr 2023 1 repository listedDiscovering inter-point connection for efficient high-dimensional feature extraction from point coordinate is a key challenge in processing point cloud.
-
8 Mar 2023 1 repository listedIn contrast to other G-invariant architectures in the literature, the preactivations of theG-DNNs presented here are able to transform by signed permutation representations (signed perm-reps) of G.
-
6 Feb 2023 1 repository listedTo solve this problem, we propose a rotation-invariant geometric relation to restore the relative pose with equivariant information for patches defined over different scales.
-
1 Jan 2023 1 repository listedPointNet is a pioneering approach in this direction that feeds the 3D point cloud data directly to a model.
-
21 Nov 2022 1 repository listedOur MATE is the first Test-Time-Training (TTT) method designed for 3D data, which makes deep networks trained for point cloud classification robust to distribution shifts occurring in test data.
-
6 Oct 2022 1 repository listedUnsupervised learning on 3D point clouds has undergone a rapid evolution, especially thanks to data augmentation-based contrastive methods.
-
1 Mar 2022 1 repository listed Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 2 harvested samples) · 2 pointer-only (licence)Manual annotation of large-scale point cloud dataset for varying tasks such as 3D object classification, segmentation and detection is often laborious owing to the irregular structure of point clouds.
-
11 Dec 2021 1 repository listedData augmentation is an important technique to reduce overfitting and improve learning performance, but existing works on data augmentation for 3D point cloud data are based on heuristics.
-
29 Nov 2021 1 repository listedStandard spatial convolutions assume input data with a regular neighborhood structure.
-
15 Oct 2021 1 repository listed3D shape representation and its processing have substantial effects on 3D shape recognition.
-
3 Feb 2021 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified (of 3 harvested samples)Data augmentation is an effective regularization strategy to alleviate the overfitting, which is an inherent drawback of the deep neural networks.
-
9 Nov 2020 1 repository listed
-
17 Oct 2020 1 repository listed Syntology official: harvested, nothing ran · 0 ran · 2 unverified (of 2 harvested samples)
-
1 Aug 2020 1 repository listed
-
29 Mar 2020 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples)
-
25 Feb 2020 1 repository listed
-
25 Dec 2019 1 repository listed
-
10 Jan 2019 1 repository listed
-
28 Nov 2018 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 6 harvested samples)
-
16 Sep 2018 1 repository listed
-
23 Jul 2018 1 repository listed
-
12 Mar 2018 1 repository listed
-
5 Dec 2017 1 repository listed
-
17 May 2017 1 repository listed
-
14 Feb 2017 1 repository listed
-
15 Nov 2016 1 repository listed
-
20 Mar 2016 1 repository listed
-
15 Jan 2013 1 repository listed
-
RW-Net: Enhancing Few-Shot Point Cloud Classification with a Wavelet Transform Projection-based Network6 Jan 2025 0 repositories listed
-
Point-GR: Graph Residual Point Cloud Network for 3D Object Classification and Segmentation4 Dec 2024 0 repositories listed
-
Efficient Spatio-Temporal Signal Recognition on Edge Devices Using PointLCA-Net21 Nov 2024 0 repositories listed
-
1 Nov 2024 0 repositories listed
-
MIRACLE 3D: Memory-efficient Integrated Robust Approach for Continual Learning on Point Clouds via Shape Model construction8 Oct 2024 0 repositories listed
-
Formula-Supervised Visual-Geometric Pre-training20 Sep 2024 0 repositories listed
-
Continual Learning in 3D Point Clouds: Employing Spectral Techniques for Exemplar Selection12 Sep 2024 0 repositories listed
-
GS-PT: Exploiting 3D Gaussian Splatting for Comprehensive Point Cloud Understanding via Self-supervised Learning8 Sep 2024 0 repositories listed
-
7 Jun 2024 0 repositories listed
-
Improving Normalization with the James-Stein Estimator1 Dec 2023 0 repositories listed
-
Fast Sparse 3D Convolution Network with VDB5 Nov 2023 0 repositories listed
-
An Interpretable Machine Learning Model with Deep Learning-based Imaging Biomarkers for Diagnosis of Alzheimer's Disease15 Aug 2023 0 repositories listed
-
MVImgNet: A Large-scale Dataset of Multi-view Images10 Mar 2023 0 repositories listed
-
Unsupervised 3D Object Learning through Neuron Activity aware Plasticity22 Feb 2023 0 repositories listed
-
HGNet: Learning Hierarchical Geometry From Points, Edges, and Surfaces1 Jan 2023 0 repositories listed
-
PointCMC: Cross-Modal Multi-Scale Correspondences Learning for Point Cloud Understanding22 Nov 2022 0 repositories listed
-
Primitive3D: 3D Object Dataset Synthesis from Randomly Assembled Primitives25 May 2022 0 repositories listed
-
Unsupervised Learning on 3D Point Clouds by Clustering and Contrasting5 Feb 2022 0 repositories listed
-
Background-Aware 3D Point Cloud Segmentationwith Dynamic Point Feature Aggregation14 Nov 2021 0 repositories listed
-
Unsupervised Contrastive Learning with Simple Transformation for 3D Point Cloud Data13 Oct 2021 0 repositories listed
-
LATFormer: Locality-Aware Point-View Fusion Transformer for 3D Shape Recognition3 Sep 2021 0 repositories listed
-
Point Discriminative Learning for Data-efficient 3D Point Cloud Analysis4 Aug 2021 0 repositories listed
-
ABD-Net: Attention Based Decomposition Network for 3D Point Cloud Decomposition9 Jul 2021 0 repositories listed
-
Dense Graph Convolutional Neural Networks on 3D Meshes for 3D Object Segmentation and Classification30 Jun 2021 0 repositories listed
-
Cross-Level Cross-Scale Cross-Attention Network for Point Cloud Representation27 Apr 2021 0 repositories listed
-
Sim2Real 3D Object Classification using Spherical Kernel Point Convolution and a Deep Center Voting Scheme10 Mar 2021 0 repositories listed
-
Self-Supervised Multi-View Learning via Auto-Encoding 3D Transformations1 Mar 2021 0 repositories listed
-
Spherical Transformer: Adapting Spherical Signal to CNNs11 Jan 2021 0 repositories listed
-
Generative VoxelNet: Learning Energy-Based Models for 3D Shape Synthesis and Analysis25 Dec 2020 0 repositories listed
-
Classification of Single-View Object Point Clouds18 Dec 2020 0 repositories listed
-
I3DOL: Incremental 3D Object Learning without Catastrophic Forgetting16 Dec 2020 0 repositories listed
-
Generalized Multi-view Shared Subspace Learning using View Bootstrapping12 May 2020 0 repositories listed
-
L3DOC: Lifelong 3D Object Classification12 Dec 2019 0 repositories listed
-
Data-Free Point Cloud Network for 3D Face Recognition12 Nov 2019 0 repositories listed
-
Multi-Task, Multi-Channel, Multi-Input Learning for Mental Illness Detection using Social Media Text1 Nov 2019 0 repositories listed
-
Addressing the Sim2Real Gap in Robotic 3D Object Classification28 Oct 2019 0 repositories listed
-
ClusterNet: Deep Hierarchical Cluster Network With Rigorously Rotation-Invariant Representation for Point Cloud Analysis1 Jun 2019 0 repositories listed
-
1 Jun 2019 0 repositories listed
-
28 Feb 2019 0 repositories listed
-
3DTI-Net: Learn Inner Transform Invariant 3D Geometry Features using Dynamic GCN15 Dec 2018 0 repositories listed
-
SPNet: Deep 3D Object Classification and Retrieval using Stereographic Projection5 Nov 2018 0 repositories listed
-
Spherical Convolutional Neural Network for 3D Point Clouds21 May 2018 0 repositories listed
-
Deep 2.5D Vehicle Classification with Sparse SfM Depth Prior for Automated Toll Systems9 May 2018 0 repositories listed
-
3D Object Classification via Spherical Projections12 Dec 2017 0 repositories listed
-
Wide and deep volumetric residual networks for volumetric image classification18 Sep 2017 0 repositories listed
-
FusionNet: 3D Object Classification Using Multiple Data Representations19 Jul 2016 0 repositories listed
Syntology lines on 11 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; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections