</> Code with Papers by Syntology

Datasets › ShapeNet

ShapeNet

Introduced by Angel X. Chang et al. in ShapeNet: An Information-Rich 3D Model Repository1 Jan 2015 archive 2025-07-28

ShapeNet is a large scale repository for 3D CAD models developed by researchers from Stanford University, Princeton University and the Toyota Technological Institute at Chicago, USA. The repository contains over 300M models with 220,000 classified into 3,135 classes arranged using WordNet hypernym-hyponym relationships. ShapeNet Parts subset contains 31,693 meshes categorised into 16 common object classes (i.e. table, chair, plane etc.). Each shapes ground truth contains 2-5 parts (with a total of 50 part classes).

Source: A review on deep learning techniques for 3D sensed data classification Image Source: ShapeNet: An Information-Rich 3D Model Repository

HomepageBenchmarksPapers JSON

Benchmarks archive 2025-07-28

All 13 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

First row (archive order)PaperCode
3D Part Segmentation ShapeNet-Part GeomGCNN Instance Average IoU 89.1 Exploiting Local Geometry for Feature and Graph... — 67 Compare
Point Cloud Completion ShapeNet ODGNet Chamfer Distance 6.50 Orthogonal Dictionary Guided Shape Completion Network... corecai163/ODGNet 11 Compare
3D Reconstruction ShapeNet MD-GON IoU 92.8 Mixing-Denoising Generalizable Occupancy Networks — 8 Compare
Single-View 3D Reconstruction ShapeNet SDFDiff 3DIoU 0.6674 SDFDiff: Differentiable Rendering of Signed Distance... YueJiang-nj/CVPR2020-SDFDiff 7 Compare
Point Cloud Generation ShapeNet Airplane LION 1-NNA-CD 53.47 LION: Latent Point Diffusion Models for 3D Shape Generation nv-tlabs/LION +1 5 Compare
Point Cloud Generation ShapeNet Car DiT-3D 1-NNA-CD 51.04 DiT-3D: Exploring Plain Diffusion Transformers for 3D... DiT-3D/DiT-3D 5 Compare
Point Cloud Generation ShapeNet Chair DiT-3D 1-NNA-CD 51.99 DiT-3D: Exploring Plain Diffusion Transformers for 3D... DiT-3D/DiT-3D 5 Compare
Semantic Segmentation ShapeNet PatchFormer Mean IoU 86.5% PatchFormer: An Efficient Point Transformer with Patch Attention — 5 Compare
Training-free 3D Part Segmentation ShapeNet-Part Point-NN mIoU 74.0 Parameter is Not All You Need: Starting from... zrrskywalker/point-nn +2 3 Compare
Point Cloud Generation ShapeNet DiT-3D CD 50.72 — — 2 Compare
3D Object Reconstruction ShapeNet SoftRas (full) 3DIoU 0.6464 Soft Rasterizer: A Differentiable Renderer for... ShichenLiu/SoftRas +1 1 Compare
Novel View Synthesis ShapeNet Car Multi-view to Novel View SSIM 0.923 Multi-view to Novel view: Synthesizing Novel Views with... shaohua0116/Multiview2Novelview 1 Compare
Novel View Synthesis ShapeNet Chair Multi-view to Novel View SSIM 0.895 Multi-view to Novel view: Synthesizing Novel Views with... shaohua0116/Multiview2Novelview 1 Compare

Papers archive 2025-07-28

30 shown of 93 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 1,947. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.

DateSamples run Syntology
AdaCrossNet: Adaptive Dynamic Loss Weighting for Cross-Modal Contrastive Point Cloud Learning 1 1 2 Jan 2025 not harvested
Rethinking Masked Representation Learning for 3D Point Cloud Understanding 1 1 26 Dec 2024 not harvested
Beyond local patches: Preserving global–local interactions by enhancing self-attention via 3D point cloud tokenization 0 1 1 Nov 2024 not harvested
3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning 0 1 24 Sep 2024 not harvested
Point-JEPA: A Joint Embedding Predictive Architecture for Self-Supervised Learning on Point Cloud 1 1 25 Apr 2024 not harvested
AVS-Net: Point Sampling with Adaptive Voxel Size for 3D Scene Understanding 1 1 27 Feb 2024 not harvested
Mixing-Denoising Generalizable Occupancy Networks 0 1 20 Nov 2023 not harvested
Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation 1 1 6 Aug 2023 not harvested
Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models 1 1 27 Jul 2023 not harvested
DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation 1 3 4 Jul 2023 ran 2 of 3 samples (1 unverified; 1 pointer-only for licence)
Learning Geometric Transformation for Point Cloud Completion 2 1 8 Jun 2023 not harvested
Exploiting Inductive Bias in Transformer for Point Cloud Classification and Segmentation 1 1 27 Apr 2023 not harvested
Self-positioning Point-based Transformer for Point Cloud Understanding 1 1 29 Mar 2023 ran 1 of 12 samples (11 unverified)
Point2Vec for Self-Supervised Representation Learning on Point Clouds 1 1 29 Mar 2023 ran 4 of 6 samples (2 unverified)
Orthogonal Dictionary Guided Shape Completion Network for Point Cloud 1 1 24 Mar 2023 not harvested
Parametric Surface Constrained Upsampler Network for Point Cloud 1 1 14 Mar 2023 ran 4 of 6 samples (2 unverified; 6 pointer-only for licence)
Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis 3 1 14 Mar 2023 ran 1 of 2 samples (1 unverified; 2 pointer-only for licence)
Attention-based Point Cloud Edge Sampling 1 2 28 Feb 2023 ran 1 of 1 samples (0 unverified)
AdaPoinTr: Diverse Point Cloud Completion with Adaptive Geometry-Aware Transformers 1 1 11 Jan 2023 ran 4 of 6 samples (2 unverified)
PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning 2 1 21 Nov 2022 ran 5 of 12 samples (7 unverified)
SageMix: Saliency-Guided Mixup for Point Clouds 1 2 13 Oct 2022 ran 0 of 1 samples (1 unverified)
LION: Latent Point Diffusion Models for 3D Shape Generation 2 4 12 Oct 2022 not harvested
Diffusion Unit: Interpretable Edge Enhancement and Suppression Learning for 3D Point Cloud Segmentation 1 1 20 Sep 2022 not harvested
P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting 1 1 4 Aug 2022 ran 1 of 10 samples (9 unverified)
Few 'Zero Level Set'-Shot Learning of Shape Signed Distance Functions in Feature Space 1 1 9 Jul 2022 not harvested
PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies 3 1 9 Jun 2022 ran 7 of 17 samples (10 unverified)
PointVector: A Vector Representation In Point Cloud Analysis 1 1 21 May 2022 ran 1 of 11 samples (10 unverified)
Snowflake Point Deconvolution for Point Cloud Completion and Generation with Skip-Transformer 1 1 18 Feb 2022 not harvested
POCO: Point Convolution for Surface Reconstruction 1 1 5 Jan 2022 ran 4 of 6 samples (2 unverified; 6 pointer-only for licence)
PointCLIP: Point Cloud Understanding by CLIP 2 1 4 Dec 2021 not harvested

The full list of 93 is in the JSON twin.

Dataset loaders archive 2025-07-28

shapenet.cs.stanford.edu/media/shapenet_part_seg_hdf5_data.zipZhang-VISLab/Learning-to-Segment-3D-Point-Clouds-in-2D-Image-Spacetfpytorch

1 loader as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

Semantic Segmentation3D ReconstructionNovel View SynthesisSingle-View 3D Reconstruction3D Object ReconstructionPoint Cloud GenerationPoint Cloud Completion3D Part SegmentationTraining-free 3D Part Segmentation

License archive 2025-07-28

Custom (non-commerical)

Modalities archive 2025-07-28

Images3DPoint cloud

Languages archive 2025-07-28

Chinese

Variants archive 2025-07-28

  • ShapeNet
  • ShapeNet Car
  • ShapeNet Chair
  • ShapeNet-Part
  • ShapeNet Airplane

5 variant names, as the archive lists them.

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