3D

🐯 3D Models trained on 3DCoMPaT++

We provide here some 3D models trained on the 3DCoMPaT dataset. This repo includes the code for 3d Shape Classification and Part Segmentation on 3DCoMPaT dataset for both coarse and fine grained versions using prevalent 3D vision algorithms, including PointNet++, DGCNN, PCT, PointStack, and CurveNet in pytorch.

You can find the pretrained models and log files in gdrive.

Results

Segmentation

Fine-grained

Model	Number of points	Accuracy	Shape-aware mIOU	Shape-agnostic mIOU	ckpt
PCT	2048	70.49	81.31	49.09	gdrive
PointNet2 partseg_ssg	2048	71.09	80.01	50.39	gdrive
Curvenet	2048	72.49	81.37	53.09	gdrive
PointNeXt	2048	82.07	83.92	63.72	gdrive

Coarse-grained

Model	Number of points	Accuracy	Shape-aware mIOU	Shape-agnostic mIOU	ckpt
PCT	2048	80.64	75.48	66.95	gdrive
PointNet2 partseg_ssg	2048	84.72	77.98	73.79	gdrive
Curvenet	2048	86.01	80.64	76.32	gdrive
PointNeXt	2048	94.17	86.80	85.45	gdrive

Classification

Model	Number of points	Accuracy	ckpt
DGCNN	2048	78.85	gdrive
PCT	2048	68.88	gdrive
PointNet2 cls_msg	2048	84.10	gdrive
PointStack	2048	83.04	gdrive
Curvenet	2048	85.14	gdrive
PointNeXt	2048	83.01	gdrive