前往PC端下载数据
Description
ModelNet 数据集共有 662 种目标分类，127915 个 CAD 模型，以及 10 类标记过方向的数据，旨在为计算机视觉、计算机图形学、机器人和认知科学的研究人员提供全面的物体 3D 模型。
该数据集包含了三个子集：
ModelNet10 为 10 个标记朝向的子集数据；
ModelNet40 为 40 个类别的三维模型；
Aligned40 为 40 类标记的三维模型。
ModelNet 数据集由普林斯顿视觉与机器人实验室于 2015 年发布，主要发布人为 N. Sedaghat, M. Zolfaghari, E. Amiri and T. Brox，相关论文有《3D ShapeNets: A Deep Representation for Volumetric Shapes》
ModelNet Benchmark Leaderboard
Please email Shuran Song to add or update your results.
In your email please provide following information in this format:
Algorithm Name, ModelNet40 Classification, ModelNet40 Retrieval, ModelNet10 Classification, ModelNet10 Retrieval
Author list, Paper title, Conference. link to paper.
Example:
3D-DescriptorNet, -, -, -,92.4%,-
Jianwen Xie, Zilong Zheng, Ruiqi Gao, Wenguan Wang, Song-Chun Zhu, and
Ying Nian Wu, Learning Descriptor Networks for 3D Shape Synthesis and
Analysis. CVPR 2018, http://...
| Algorithm | ModelNet40 Classification (Accuracy) | ModelNet40 Retrieval (mAP) | ModelNet10 Classification (Accuracy) | ModelNet10 Retrieval (mAP) |
|---|---|---|---|---|
| RS-CNN[63] | 93.6% | - | - | - |
| LP-3DCNN[62] | 92.1% | - | 94.4% | - |
| LDGCNN[61] | 92.9% | - | - | - |
| Primitive-GAN[60] | 86.4% | - | 92.2% | - |
| 3DCapsule [59] | 92.7% | - | 94.7% | - |
| 3D2SeqViews [58] | 93.40% | 90.76% | 94.71% | 92.12% |
| OrthographicNet [57] | - | - | 88.56% | 86.85% |
| Ma et al. [56] | 91.05% | 84.34% | 95.29% | 93.19% |
| MLVCNN [55] | 94.16% | 92.84% | - | - |
| iMHL [54] | 97.16% | - | - | - |
| HGNN [53] | 96.6% | - | - | - |
| SPNet [52] | 92.63% | 85.21% | 97.25% | 94.20% |
| MHBN [51] | 94.7 | - | 95.0 | - |
| VIPGAN [50] | 91.98 | 89.23 | 94.05 | 90.69 |
| Point2Sequence [49] | 92.60 | - | 95.30 | - |
| Triplet-Center Loss [48] | - | 88.0% | - | - |
| PVNet[47] | 93.2% | 89.5% | - | - |
| GVCNN[46] | 93.1% | 85.7% | - | - |
| MLH-MV[45] | 93.11% | 94.80% | ||
| MVCNN-New[44] | 95.0% | |||
| SeqViews2SeqLabels[43] | 93.40% | 89.09% | 94.82% | 91.43% |
| G3DNet[42] | 91.13% | 93.1% | ||
| VSL [41] | 84.5% | 91.0% | ||
| 3D-CapsNets[40] | 82.73% | 70.1% | 93.08% | 88.44% |
| KCNet[39] | 91.0% | 94.4% | ||
| FoldingNet[38] | 88.4% | 94.4% | ||
| binVoxNetPlus[37] | 85.47% | 92.32% | ||
| DeepSets[36] | 90.3% | |||
| 3D-DescriptorNet[35] | 92.4% | |||
| SO-Net[34] | 93.4% | 95.7% | ||
| Minto et al.[33] | 89.3% | 93.6% | ||
| RotationNet[32] | 97.37% | 98.46% | ||
| LonchaNet[31] | 94.37 | |||
| Achlioptas et al. [30] | 84.5% | 95.4% | ||
| PANORAMA-ENN [29] | 95.56% | 86.34% | 96.85% | 93.28% |
| 3D-A-Nets [28] | 90.5% | 80.1% | ||
| Soltani et al. [27] | 82.10% | |||
| Arvind et al. [26] | 86.50% | |||
| LonchaNet [25] | 94.37% | |||
| 3DmFV-Net [24] | 91.6% | 95.2% | ||
| Zanuttigh and Minto [23] | 87.8% | 91.5% | ||
| 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] | 88.93% | 93.94% | ||
| 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% |