Objaverse (I): 56.50Objaverse (Average): 54.00Objaverse (C): 51.50
Papers with Code · CC BY-SA 4.0
3D Object Classification
3D Object Classification is the task of predicting the class of a 3D object point cloud. It is a voxel level prediction where each voxel is classified into a category. The popular benchmark for this task is the ModelNet dataset. The models for this task are usually evaluated with the Classification Accuracy metric.
Image: Sedaghat et al
논문
Objaverse (Average): 54.50
Accuracy: 90
Accuracy: 93.1
Objaverse (I): 60.00Objaverse (Average): 60.25Objaverse (C): 60.50
Objaverse (I): 6.00Objaverse (Average): 5.25Objaverse (C): 4.50
Top-5 Accuracy: 0.7Top-10 Accuracy: 0.8
Classification Accuracy: 89.3
Objaverse (I): 49.00Objaverse (Average): 45.25Objaverse (C): 41.50
Classification Accuracy: 91.49
Classification Accuracy: 93.6
Classification Accuracy: 89.9
Accuracy: 93.8
Accuracy: 94.93
mean average precision: 0.9858
Classification Accuracy: 89.3