Goal

The goal of the Princeton ModelNet project is to provide researchers in computer vision, computer graphics, robotics and cognitive science, with a comprehensive clean collection of 3D CAD models for objects. To build the core of the dataset, we compiled a list of the most common object categories in the world, using the statistics obtained from the SUN database. Once we established a vocabulary for objects, we collected 3D CAD models belonging to each object category using online search engines by querying for each object category term. Then, we hired human workers on Amazon Mechanical Turk to manually decide whether each CAD model belongs to the specified cateogries, using our in-house designed tool with quality control. To obtain a very clean dataset, we choose 10 popular object categories, and manually deleted the models that did not belong to these categories. Furthermore, we manually aligned the orientation of the CAD models for this 10-class subset as well. We provide both the 10-class subset and the full dataset for download.

Download 10-Class Orientation-aligned Subset

ModelNet10.zip: this ZIP file contains CAD models from the 10 categories used to train the deep network in our 3D deep learning project. Training and testing split is included in the file. The CAD models are completely cleaned inhouse, and the orientations of the models (not scale) are manually aligned by ourselves.

Download 40-Class Subset

ModelNet40.zip: this ZIP file contains CAD models from the 40 categories used to train the deep network in our 3D deep learning project. Training and testing split is included in the file. The CAD models are completely cleaned inhouse by ourselves.

The CAD models are in Object File Format (OFF). We also provide Matlab functions to read and visualize OFF files in our Princeton Vision Toolkit (PVT).

Leaderboard

Please email Shuran Song to add or update your results.

AlgorithmModelNet40
Classification
(Accuracy)
ModelNet40
Retrieval
(mAP)
ModelNet10
Classification
(Accuracy)
ModelNet10
Retrieval
(mAP)
Wang et al. [22]93.8%
ECC [21]83.2%90.0%
PANORAMA-NN [20]90.7%83.5%91.1%87.4%
MVCNN-MultiRes [19]91.4%
FPNN [18]88.4%
PointNet[17]89.2%
Klokov and Lempitsky[16]91.8% 94.0%
LightNet[15]86.90% 93.39%
Xu and Todorovic[14]81.26% 88.00%
Geometry Image [13]83.9% 51.3%88.4%74.9%
Set-convolution [11]90%
PointNet [12]77.6%
3D-GAN [10]83.3%91.0%
VRN Ensemble [9]95.54%97.14%
ORION [8] 93.8%
FusionNet [7]90.8%93.11%
Pairwise [6]90.7%92.8%
MVCNN [3]90.1%79.5%
GIFT [5] 83.10%81.94% 92.35%91.12%
VoxNet [2]83%92%
DeepPano [4]77.63%76.81%85.45%84.18%
3DShapeNets [1]77%49.2%83.5%68.3%

[1] Z. Wu, S. Song, A. Khosla, F. Yu, L. Zhang, X. Tang and J. Xiao. 3D ShapeNets: A Deep Representation for Volumetric Shapes. CVPR2015.
[2] D. Maturana and S. Scherer. VoxNet: A 3D Convolutional Neural Network for Real-Time Object Recognition. IROS2015.
[3] H. Su, S. Maji, E. Kalogerakis, E. Learned-Miller. Multi-view Convolutional Neural Networks for 3D Shape Recognition. ICCV2015.
[4] B Shi, S Bai, Z Zhou, X Bai. DeepPano: Deep Panoramic Representation for 3-D Shape Recognition. Signal Processing Letters 2015.
[5] Song Bai, Xiang Bai, Zhichao Zhou, Zhaoxiang Zhang, Longin Jan Latecki. GIFT: A Real-time and Scalable 3D Shape Search Engine. CVPR 2016.
[6] Edward Johns, Stefan Leutenegger and Andrew J. Davison. Pairwise Decomposition of Image Sequences for Active Multi-View Recognition CVPR 2016.
[7] Vishakh Hegde, Reza Zadeh 3D Object Classification Using Multiple Data Representations.
[8] Nima Sedaghat, Mohammadreza Zolfaghari, Thomas Brox Orientation-boosted Voxel Nets for 3D Object Recognition.
[9] Andrew Brock, Theodore Lim, J.M. Ritchie, Nick Weston Generative and Discriminative Voxel Modeling with Convolutional Neural Networks.
[10] Jiajun Wu, Chengkai Zhang, Tianfan Xue, William T. Freeman, Joshua B. Tenenbaum. Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling. NIPS 2016
[11] Siamak Ravanbakhsh, Jeff Schneider, Barnabas Poczos. Deep Learning with sets and point clouds
[12] A. Garcia-Garcia, F. Gomez-Donoso†, J. Garcia-Rodriguez, S. Orts-Escolano, M. Cazorla, J. Azorin-Lopez. PointNet: A 3D Convolutional Neural Network for Real-Time Object Class Recognition
[13] Ayan Sinha, Jing Bai, Karthik Ramani. Deep Learning 3D Shape Surfaces Using Geometry Images ECCV 2016
[14] Xu Xu and Sinisa Todorovic. Beam Search for Learning a Deep Convolutional Neural Network of 3D Shapes
[15] A Lightweight 3D Convolutional Neural Network for Real-Time 3D Object Recognition
[16] Roman Klokov, Victor Lempitsky Escape from Cells: Deep Kd-Networks for The Recognition of 3D Point Cloud Models
[17] Charles R. Qi, Hao Su, Kaichun Mo, and Leonidas J. Guibas. PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. CVPR 2017.
[18] Yangyan Li, Soeren Pirk, Hao Su, Charles R. Qi, and Leonidas J. Guibas. FPNN: Field Probing Neural Networks for 3D Data. NIPS 2016.
[19] Charles R. Qi, Hao Su, Matthias Niessner, Angela Dai, Mengyuan Yan, and Leonidas J. Guibas.
Volumetric and Multi-View CNNs for Object Classification on 3D Data. CVPR 2016.
[20] K. Sfikas, T. Theoharis and I. Pratikakis.
Exploiting the PANORAMA Representation for Convolutional Neural Network Classification and Retrieval. 3DOR2017.
[21] Martin Simonovsky, Nikos Komodakis
Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs.
[22] Chu Wang, Marcello Pelillo, Kaleem Siddiqi.
Dominant Set Clustering and Pooling for Multi-View 3D Object Recognition. BMVC 2017.

Download Full Dataset

Please email Shuran Song to obtain the Matlab toolbox for downloading.

Citation

If you find this dataset useful, please cite the following paper:

Z. Wu, S. Song, A. Khosla, F. Yu, L. Zhang, X. Tang and J. Xiao
3D ShapeNets: A Deep Representation for Volumetric Shapes
Proceedings of 28th IEEE Conference on Computer Vision and Pattern Recognition (CVPR2015)
Oral Presentation ·  3D Deep Learning Project Webpage

Copyright

All CAD models are downloaded from the Internet and the original authors hold the copyright of the CAD models. The label of the data was obtained by us via Amazon Mechanical Turk service and it is provided freely. This dataset is provided for the convenience of academic research only.