3D Pointcloud w/o color Comparison

Compare pointcloud classification results on various methods
Method Apple10 Fruits Vegetables Packages Full
PointNet[1] 18.93 33.16 35.15 71.61 37.61
PointNet++[2] 26.20 47.98 54.11 82.70 48.65
DGCNN[3] 19.04 37.01 42.16 79.44 44.19
PCT[4] 18.95 32.39 43.42 75.34 39.67
PointMLP[5] 19.16 36.38 47.29 79.94 45.72
PointNeXt[6] 21.63 40.58 48.40 81.35 47.73

3D Pointcloud w/ color Comparison

Compare pointcloud+color classification results on various methods
Method Apple10 Fruits Vegetables Packages Full
PointNet[1] 78.35 96.42 97.00 97.85 92.62
PointNet++[2] 84.00 97.58 98.25 98.46 95.21
DGCNN[3] 83.59 98.01 97.88 98.53 96.20
PCT[4] 82.14 97.89 97.63 97.97 94.19
PointMLP[5] 90.18 97.75 97.68 98.38 96.82
PointNeXt[6] 84.81 97.36 97.37 98.13 94.44

2D Image Patch Classification

Compare Image patch classification results
Method Apple10 Fruits Vegetables Packages Full
SwinTransformer[7] 85.10 98.50 98.40 98.30 98.50

References

[1] Qi, C. R., Su, H., Mo, K., & Guibas, L. J. (2017). Pointnet: Deep learning on point sets for 3d classification and segmentation. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 652-660).
[2] Qi, C. R., Yi, L., Su, H., & Guibas, L. J. (2017). Pointnet++: Deep hierarchical feature learning on point sets in a metric space. In Advances in neural information processing systems (pp. 5099-5108).
[3] Wang, Y., Sun, Y., Liu, Z., Sarma, S. E., Bronstein, M. M., & Solomon, J. M. (2019). Dynamic graph cnn for learning on point clouds. Acm Transactions On Graphics (tog), 38(5), 1-12.
[4] Guo, Meng-Hao, et al. "Pct: Point cloud transformer." Computational Visual Media 7.2 (2021): 187-199.
[5] Ma, Xu, et al. "Rethinking network design and local geometry in point cloud: A simple residual mlp framework." arXiv preprint arXiv:2202.07123 (2022).
[6] Qian, Guocheng, et al. "PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies." arXiv preprint arXiv:2206.04670 (2022).
[7] Liu, Ze, et al. "Swin transformer: Hierarchical vision transformer using shifted windows." Proceedings of the IEEE/CVF international conference on computer vision. 2021.