Browse State-of-the-Art › 3D Classification
3D Classification
42 papers with code · 1 benchmark · 15 datasets 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 |
|---|---|---|---|---|---|
| U-10: United-10 COVID19 CT Dataset (2 rows) | U-10 Model | Virtual imaging trials improved the transparency and reliability... | 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
15 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.
Papers archive 2025-07-28
archive papers tagged: 79 · with a code link: 42 · where Syntology ran a sample: 12 (8 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (12 of 79 tagged: 8 with a run with no instrument failure, 4 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 79 of 79, 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.
-
9 Jun 2022 3 repositories listed Syntology official (archive's flag): 3 ran · 10 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 6 where Syntology's instrument failed) · 7 unverified (of 17 harvested samples)In this work, we revisit the classical PointNet++ through a systematic study of model training and scaling strategies, and offer two major contributions.
-
17 Nov 2017 3 repositories listed Syntology official (archive's flag): 1 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)We address the problem of 3D rotation equivariance in convolutional neural networks.
-
17 Aug 2023 2 repositories listedThe study underscores the potential of VIT to improve the reproducibility and clinical relevance of AI systems in medical imaging.
-
10 Aug 2023 2 repositories listed Syntology official (archive's flag): 16 ran · 16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 2 honoured, 1 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 6 unverified (of 22 harvested samples) · 22 pointer-only (licence)In this study, we develop a general mechanism to increase neural network robustness based on focus analysis.
-
21 Nov 2022 2 repositories listed Syntology official (archive's flag): 8 ran · 8 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; 4 where Syntology's instrument failed) · 4 unverified (of 12 harvested samples) · 4 pointer-only (licence)In this paper, we first collaborate CLIP and GPT to be a unified 3D open-world learner, named as PointCLIP V2, which fully unleashes their potential for zero-shot 3D classification, segmentation, and detection.
-
30 Nov 2021 2 repositories listed Syntology community repositories only · 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) · 4 unverified (of 6 harvested samples)To this end, we introduce the concept of the multi-view point cloud (Voint cloud), representing each 3D point as a set of features extracted from several view-points.
-
22 Nov 2021 2 repositories listedSecondly, the original dataset was processed via anatomy-relevant masking of slice, removing none-representative slices from the CT volume, and hyperparameters tuning.
-
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.
-
9 Feb 2020 2 repositories listedThe PointHop method was recently proposed by Zhang et al. for 3D point cloud classification with unsupervised feature extraction.
-
24 Nov 2024 1 repository listedPurpose: This study investigated how nodule segmentation and surrounding peritumoral regions influence radionics-based lung cancer classification.
-
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.
-
21 Sep 2024 1 repository listedSemi-supervised learning (SSL) has shown its effectiveness in learning effective 3D representation from a small amount of labelled data while utilizing large unlabelled data.
-
19 Aug 2024 1 repository listedIn contrast, we propose a tokenizer with linear-time complexity, which enables the efficient embedding of a flexible number of tokens.
-
2 Jul 2024 1 repository listedTo test our method and ensure the reproducibility of our results, we chose a standardized collection of MRI data from the Alzheimer's Disease Neuroimaging Initiative (ADNI).
-
23 May 2024 1 repository listedA fundamental limitation to the development of 3D saliency methods is the lack of a benchmark to quantitatively assess these on 3D data.
-
27 Dec 2023 1 repository listedThe large model GMViT achieves excellent 3D classification and retrieval results on the benchmark datasets ModelNet, ShapeNetCore55, and MCB.
-
20 Aug 2023 1 repository listedA well-trained lens with a ViT backbone has the potential to serve as one of these foundation models, supervising the learning of subsequent modalities.
-
6 Aug 2023 1 repository listedInsufficient synergy neglects the idea that a robust 3D representation should align with the joint vision-language space, rather than independently aligning with each modality.
-
18 May 2023 1 repository listed Syntology 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) · 4 unverified (of 7 harvested samples) · 2 pointer-only (licence)Due to their alignment with CLIP embeddings, our learned shape representations can also be integrated with off-the-shelf CLIP-based models for various applications, such as point cloud captioning and point…
-
14 May 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)It achieves a new SOTA of 50.
-
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.
-
10 Dec 2022 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)Then, ULIP learns a 3D representation space aligned with the common image-text space, using a small number of automatically synthesized triplets.
-
9 Dec 2022 1 repository listedWe train and evaluate PointNeXt on ModelNet40 (synthetic), ScanObjectNN (real-world), and a recent large-scale, real-world grocery dataset, i. e., 3DGrocery100.
-
14 Sep 2022 1 repository listedAdversarial contrastive learning (ACL) is considered an effective way to improve the robustness of pre-trained models.
-
8 Sep 2022 1 repository listedAmong these methods, the Simple View model demonstrates that features from six orthogonal perspective projections of a point cloud achieved comparable 3D classification.
-
2 May 2022 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)In the existing work, each point in the cloud may inevitably be selected as the neighbors of multiple aggregation centers, as all centers will gather neighbor features from the whole point cloud independently.
-
1 Jan 2022 1 repository listedThe proposed network synergically combines 3D CNN, 2D CNN, and Transformer for accurate AD classification.
-
17 Dec 2021 1 repository listedIt results in a serious issue of lagged gradient, making the learned attack at the current step ineffective due to the architecture changes afterward.
-
22 Oct 2021 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) · 1 unverified (of 2 harvested samples) · 2 pointer-only (licence)This paper explores how the coherence of different modelities of 3D data (e. g. point cloud, image, and mesh) can be used to improve data efficiency for both 3D classification and retrieval tasks.
-
19 Oct 2021 1 repository listedWe propose a novel technique of dynamically oriented and scaled ellipsoid based on unique local information to capture the local geometry better.
-
27 Aug 2021 1 repository listed
-
4 Jun 2021 1 repository listed Syntology official (archive's flag): 5 ran · 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)
-
29 Apr 2021 1 repository listed
-
23 Dec 2020 1 repository listed
-
1 Dec 2020 1 repository listed
-
31 Oct 2020 1 repository listed
-
1 Aug 2020 1 repository listed
-
9 Jun 2020 1 repository listed
-
1 Jun 2020 1 repository listed
-
27 Feb 2020 1 repository listed
-
10 Dec 2019 1 repository listed
-
17 Apr 2019 1 repository listed
-
MVIP -- A Dataset and Methods for Application Oriented Multi-View and Multi-Modal Industrial Part Recognition21 Feb 2025 0 repositories listed
-
Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding16 Jan 2025 0 repositories listed
-
Mitigating Ambiguities in 3D Classification with Gaussian Splatting1 Jan 2025 0 repositories listed
-
Seeing is Not Believing: Adversarial Natural Object Optimization for Hard-Label 3D Scene Attacks1 Jan 2025 0 repositories listed
-
1 Nov 2024 0 repositories listed
-
Hyperbolic Image-and-Pointcloud Contrastive Learning for 3D Classification24 Sep 2024 0 repositories listed
-
Computer Vision Intelligence Test Modeling and Generation: A Case Study on Smart OCR14 Sep 2024 0 repositories listed
-
ConDense: Consistent 2D/3D Pre-training for Dense and Sparse Features from Multi-View Images30 Aug 2024 0 repositories listed
-
Diff3Dformer: Leveraging Slice Sequence Diffusion for Enhanced 3D CT Classification with Transformer Networks24 Jun 2024 0 repositories listed
-
Adapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Vision5 Jun 2024 0 repositories listed
-
No Captions, No Problem: Captionless 3D-CLIP Alignment with Hard Negatives via CLIP Knowledge and LLMs4 Jun 2024 0 repositories listed
-
Cross-Dimensional Medical Self-Supervised Representation Learning Based on a Pseudo-3D Transformation3 Jun 2024 0 repositories listed
-
MM-Mixing: Multi-Modal Mixing Alignment for 3D Understanding28 May 2024 0 repositories listed
-
Deep Models for Multi-View 3D Object Recognition: A Review23 Apr 2024 0 repositories listed
-
Automated Classification of Body MRI Sequence Type Using Convolutional Neural Networks12 Feb 2024 0 repositories listed
-
MV-CLIP: Multi-View CLIP for Zero-shot 3D Shape Recognition30 Nov 2023 0 repositories listed
-
Advancements in Point Cloud Data Augmentation for Deep Learning: A Survey23 Aug 2023 0 repositories listed
-
Improved Cryo-EM Pose Estimation and 3D Classification through Latent-Space Disentanglement9 Aug 2023 0 repositories listed
-
Advancing Smart Malnutrition Monitoring: A Multi-Modal Learning Approach for Vital Health Parameter Estimation31 Jul 2023 0 repositories listed
-
DiffCLIP: Leveraging Stable Diffusion for Language Grounded 3D Classification25 May 2023 0 repositories listed
-
Self-supervised Learning by View Synthesis22 Apr 2023 0 repositories listed
-
Variational Relational Point Completion Network for Robust 3D Classification18 Apr 2023 0 repositories listed
-
Automatic Aortic Valve Pathology Detection from 3-Chamber Cine MRI with Spatio-Temporal Attention Maps12 Apr 2023 0 repositories listed
-
Comparing 3D deformations between longitudinal daily CBCT acquisitions using CNN for head and neck radiotherapy toxicity prediction7 Mar 2023 0 repositories listed
-
Classification of FIB/SEM-tomography images for highly porous multiphase materials using random forest classifiers28 Jul 2022 0 repositories listed
-
SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems10 Apr 2022 0 repositories listed
-
Localized Perturbations For Weakly-Supervised Segmentation of Glioma Brain Tumours29 Nov 2021 0 repositories listed
-
VA-GCN: A Vector Attention Graph Convolution Network for learning on Point Clouds1 Jun 2021 0 repositories listed
-
28 Mar 2021 0 repositories listed
-
Concentric Spherical GNN for 3D Representation Learning18 Mar 2021 0 repositories listed
-
The Card Shuffling Hypotheses: Building a Time and Memory Efficient Graph Convolutional Network1 Jan 2021 0 repositories listed
-
Cross-Modality 3D Object Detection16 Aug 2020 0 repositories listed
-
Region Proposal Network with Graph Prior and IoU-Balance Loss for Landmark Detection in 3D Ultrasound1 Apr 2020 0 repositories listed
-
FusionNet: Incorporating Shape and Texture for Abnormality Detection in 3D Abdominal CT Scans21 Aug 2019 0 repositories listed
-
3D Object Classification via Spherical Projections12 Dec 2017 0 repositories listed
-
Deep Learning on Lie Groups for Skeleton-based Action Recognition18 Dec 2016 0 repositories listed
-
Covariance estimation using conjugate gradient for 3D classification in Cryo-EM2 Dec 2014 0 repositories listed
Syntology lines on 12 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