Browse State-of-the-Art › 3D Shape Classification
3D Shape Classification
30 papers with code · 1 benchmark · 1 dataset archive 2025-07-28
Image: Sun et al
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
1 leaderboard table shown for this task, 1 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 |
|---|---|---|---|---|---|
| Pix3D (3 rows) | MarrNet extension (w/o Pose) | Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling | code | — | 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
1 dataset whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
No subtask under this task in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 82 · with a code link: 30 · where Syntology ran a sample: 6 (6 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (6 of 82 tagged: 6 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 82 of 82, 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.
-
27 Dec 2019 3 repositories listedTo stimulate future research, this paper presents a comprehensive review of recent progress in deep learning methods for point clouds.
-
21 Mar 2022 2 repositories 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: 1 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)Masked autoencoding has achieved great success for self-supervised learning in the image and language domains.
-
4 Dec 2020 2 repositories listedIn this thesis, we extend equivariance to other kinds of transformations, such as rotation and scaling.
-
26 Nov 2020 2 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)MVTN exhibits clear performance gains in the tasks of 3D shape classification and 3D shape retrieval without the need for extra training supervision.
-
7 Jan 2019 2 repositories listedIt has been challenging to analyze signals with mixed topologies (for example, point cloud with surface mesh).
-
28 Nov 2018 2 repositories listed Syntology 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples) · 1 pointer-only (licence)However, there is little effort on using mesh data in recent years, due to the complexity and irregularity of mesh data.
-
19 Sep 2018 2 repositories 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) · 6 unverified (of 7 harvested samples) · 3 pointer-only (licence)Deep neural networks are known to be vulnerable to adversarial examples which are carefully crafted instances to cause the models to make wrong predictions.
-
24 Mar 2024 1 repository listedWe evaluate the performance of Interpretable3D on four popular point cloud models: DGCNN, PointNet2, PointMLP, and PointNeXt.
-
Rotation-Invariant Random Features Provide a Strong Baseline for Machine Learning on 3D Point Clouds27 Jul 2023 1 repository listedSpecifically, we extend the random features method of Rahimi & Recht 2007 by deriving a version that is invariant to three-dimensional rotations and showing that it is fast to evaluate on point cloud data.
-
25 Mar 2023 1 repository listedFor example, the image branch in CrossPoint is ∼8.
-
27 Dec 2022 1 repository listedMulti-view projection techniques have shown themselves to be highly effective in achieving top-performing results in the recognition of 3D shapes.
-
23 Oct 2022 1 repository listedTransformer with its underlying attention mechanism and the ability to capture long-range dependencies makes it become a natural choice for unordered point cloud data.
-
7 Jul 2022 1 repository listedIn this paper, we explore the possibility of boosting deep 3D point cloud encoders by transferring visual knowledge extracted from deep 2D image encoders under a standard teacher-student distillation workflow.
-
29 Nov 2021 1 repository listedStandard spatial convolutions assume input data with a regular neighborhood structure.
-
19 Nov 2021 1 repository listedWe reverse the conventional design of applying convolution on voxels and attention to points.
-
15 Oct 2021 1 repository listed3D shape representation and its processing have substantial effects on 3D shape recognition.
-
7 Oct 2021 1 repository listedPoint cloud is one of the widely used techniques for representing and storing 3D geometric data.
-
22 Sep 2021 1 repository listedWe address 3D shape classification with partial point cloud inputs captured from multiple viewpoints around the object.
-
1 Sep 2021 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 3 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) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result (of 3 harvested samples) · 3 pointer-only (licence)To date, various 3D scene understanding tasks still lack practical and generalizable pre-trained models, primarily due to the intricate nature of 3D scene understanding tasks and their immense variations introduced by…
-
1 Jun 2020 1 repository listedThis paper proposes a novel probabilistic framework for the learning of unsupervised deep shape descriptors with point distribution learning.
-
1 Jun 2020 1 repository listedView-based approach that recognizes 3D shape through its projected 2D images has achieved state-of-the-art results for 3D shape recognition.
-
26 May 2020 1 repository listedAccording to our experiments under this fine-grained dataset, we find that state-of-the-art methods are significantly limited by the small variance among subcategories in the same category.
-
27 Sep 2019 1 repository listedNext, we develop nomenclature rules for pyramidal neurons and mitochondria from the reduced graph and finally learn the feature embedding for shape manipulation.
-
1 Apr 2019 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 7 harvested samples)Several popular approaches to 3D vision tasks process multiple views of the input independently with deep neural networks pre-trained on natural images, achieving view permutation invariance through a single round of…
-
6 Dec 2018 1 repository listedThis embedding encodes images with 3D shape properties and is equivariant to 3D rotations of the observed object.
-
23 Aug 2018 1 repository listedWith the recent proliferation of deep learning, various deep models with different representations have achieved the state-of-the-art performance.
-
15 May 2018 1 repository listedIn this paper, we introduce a new 3D hand gesture recognition approach based on a deep learning model.
-
16 Mar 2018 1 repository listedMost existing 3D object recognition algorithms focus on leveraging the strong discriminative power of deep learning models with softmax loss for the classification of 3D data, while learning discriminative features with…
-
14 Dec 2016 1 repository listedEach state of the beam search corresponds to a candidate CNN.
-
30 Mar 2016 1 repository listedCurrent best local descriptors are learned on a large dataset of matching and non-matching keypoint pairs.
-
A comprehensive overview of deep learning techniques for 3D point cloud classification and semantic segmentation20 May 2024 0 repositories listed
-
Ensemble Quadratic Assignment Network for Graph Matching11 Mar 2024 0 repositories listed
-
Invariant Training 2D-3D Joint Hard Samples for Few-Shot Point Cloud Recognition18 Aug 2023 0 repositories listed
-
Multi-View Representation is What You Need for Point-Cloud Pre-Training5 Jun 2023 0 repositories listed
-
APPT : Asymmetric Parallel Point Transformer for 3D Point Cloud Understanding31 Mar 2023 0 repositories listed
-
Frequency-domain Learning for Volumetric-based 3D Data Perception16 Feb 2023 0 repositories listed
-
Robust 3D Shape Classification via Non-Local Graph Attention Network1 Jan 2023 0 repositories listed
-
Rethinking Rotation Invariance with Point Cloud Registration31 Dec 2022 0 repositories listed
-
VN-Transformer: Rotation-Equivariant Attention for Vector Neurons8 Jun 2022 0 repositories listed
-
PAPooling: Graph-based Position Adaptive Aggregation of Local Geometry in Point Clouds28 Nov 2021 0 repositories listed
-
Adaptive Wavelet Transformer Network for 3D Shape Representation Learning29 Sep 2021 0 repositories listed
-
Contrastive Learning of 3D Shape Descriptor with Dynamic Adversarial Views29 Sep 2021 0 repositories listed
-
Point Cloud Learning with Transformer28 Apr 2021 0 repositories listed
-
Potential Convolution: Embedding Point Clouds into Potential Fields5 Apr 2021 0 repositories listed
-
RocNet: Recursive Octree Network for Efficient 3D Deep Representation10 Aug 2020 0 repositories listed
-
Learning Attentive and Hierarchical Representations for 3D Shape Recognition1 Aug 2020 0 repositories listed
-
Extending DeepSDF for automatic 3D shape retrieval and similarity transform estimation20 Apr 2020 0 repositories listed
-
Joint Supervised and Self-Supervised Learning for 3D Real-World Challenges15 Apr 2020 0 repositories listed
-
Self-supervised Feature Learning by Cross-modality and Cross-view Correspondences13 Apr 2020 0 repositories listed
-
Shape retrieval of non-rigid 3d human models1 Mar 2020 0 repositories listed
-
Enhancing 2D Representation via Adjacent Views for 3D Shape Retrieval1 Oct 2019 0 repositories listed
-
HRGE-Net: Hierarchical Relational Graph Embedding Network for Multi-view 3D Shape Recognition27 Aug 2019 0 repositories listed
-
View N-gram Network for 3D Object Retrieval6 Aug 2019 0 repositories listed
-
Rethinking Loss Design for Large-scale 3D Shape Retrieval3 Jun 2019 0 repositories listed
-
Deep Sketch-Shape Hashing With Segmented 3D Stochastic Viewing1 Jun 2019 0 repositories listed
-
Re-Ranking via Metric Fusion for Object Retrieval and Person Re-Identification1 Jun 2019 0 repositories listed
-
Skeleton-Based Hand Gesture Recognition by Learning SPD Matrices with Neural Networks20 May 2019 0 repositories listed
-
Non-rigid 3D shape retrieval based on multi-view metric learning20 Mar 2019 0 repositories listed
-
A Sketch Based 3D Shape Retrieval Approach Based on Efficient Deep Point-to-Subspace Metric Learning1 Mar 2019 0 repositories listed
-
Multi-feature Distance Metric Learning for Non-rigid 3D Shape Retrieval10 Jan 2019 0 repositories listed
-
Learning a Disentangled Embedding for Monocular 3D Shape Retrieval and Pose Estimation24 Dec 2018 0 repositories listed
-
PVRNet: Point-View Relation Neural Network for 3D Shape Recognition2 Dec 2018 0 repositories listed
-
Angular Triplet-Center Loss for Multi-view 3D Shape Retrieval21 Nov 2018 0 repositories listed
-
3D Pick & Mix: Object Part Blending in Joint Shape and Image Manifolds2 Nov 2018 0 repositories listed
-
3D shape retrieval basing on representatives of classes21 Oct 2018 0 repositories listed
-
A Deeper Look at 3D Shape Classifiers7 Sep 2018 0 repositories listed
-
VERAM: View-Enhanced Recurrent Attention Model for 3D Shape Classification20 Aug 2018 0 repositories listed
-
Deep Cross-modality Adaptation via Semantics Preserving Adversarial Learning for Sketch-based 3D Shape Retrieval4 Jul 2018 0 repositories listed
-
GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition1 Jun 2018 0 repositories listed
-
3D-A-Nets: 3D Deep Dense Descriptor for Volumetric Shapes with Adversarial Networks28 Nov 2017 0 repositories listed
-
3D Shape Classification Using Collaborative Representation based Projections13 Nov 2017 0 repositories listed
-
Ensemble Diffusion for Retrieval1 Oct 2017 0 repositories listed
-
Learning Barycentric Representations of 3D Shapes for Sketch-Based 3D Shape Retrieval1 Jul 2017 0 repositories listed
-
Design, Analysis and Application of A Volumetric Convolutional Neural Network1 Feb 2017 0 repositories listed
-
3D Shape Retrieval via Irrelevance Filtering and Similarity Ranking (IF/SR)30 Jan 2017 0 repositories listed
-
Facial Surface Analysis using Iso-Geodesic Curves in Three Dimensional Face Recognition System31 Aug 2016 0 repositories listed
-
GIFT: A Real-time and Scalable 3D Shape Search Engine7 Apr 2016 0 repositories listed
-
3D Deep Shape Descriptor1 Jun 2015 0 repositories listed
-
Sketch-based 3D Shape Retrieval using Convolutional Neural Networks14 Apr 2015 0 repositories listed
-
A Stable Multi-Scale Kernel for Topological Machine Learning21 Dec 2014 0 repositories listed
-
Deep Learning Representation using Autoencoder for 3D Shape Retrieval25 Sep 2014 0 repositories listed
-
Persistence-based Structural Recognition1 Jun 2014 0 repositories listed
Syntology lines on 6 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