Training Free 3D Point Cloud Classification 1

Accuracy (%)

Need 3D Data?

Results

Performance results of various models on this benchmark

			Paper Title
Point-GN	86.4	Yes	Point-GN: A Non-Parametric Network Using Gaussian Positional Encoding for Point Cloud Classification
Point-NN	64.9	Yes	Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis
PointCLIP V2	35.4	No	PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning
CLIP2Point	23.2	Yes	CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training
CALIP	16.9	No	CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention
PointCLIP	15.4	No	PointCLIP: Point Cloud Understanding by CLIP

0 of 6 row(s) selected.