Training-free 3D Point Cloud Classification on ScanObjectNN

Metric: Accuracy (%) (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Hide extra data

Sort:

#	Model↕	Accuracy (%)▼	Extra Data	Paper	Date↕	Code
1	Point-GN	86.4	No	Point-GN: A Non-Parametric Network Using Gaussia...	2024-12-04	Code
2	Point-NN	64.9	No	Parameter is Not All You Need: Starting from Non...	2023-03-14	Code
3	PointCLIP V2	35.4	Yes	PointCLIP V2: Prompting CLIP and GPT for Powerfu...	2022-11-21	Code
4	CLIP2Point	23.2	Yes	CLIP2Point: Transfer CLIP to Point Cloud Classif...	2022-10-03	Code
5	CALIP	16.9	Yes	CALIP: Zero-Shot Enhancement of CLIP with Parame...	2022-09-28	Code
6	PointCLIP	15.4	Yes	PointCLIP: Point Cloud Understanding by CLIP	2021-12-04	Code

#1Point-GNSOTA
86.4
Accuracy (%)· 2024-12-04
Point-GN: A Non-Parametric Network Using Gaussian Positional Encoding for Point Cloud Classification Code
#2Point-NNSOTA
64.9
Accuracy (%)· 2023-03-14
Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis Code
#3PointCLIP V2SOTA
35.4
Accuracy (%)· Extra Data· 2022-11-21
PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning Code
#4CLIP2PointSOTA
23.2
Accuracy (%)· Extra Data· 2022-10-03
CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training Code
#5CALIPSOTA
16.9
Accuracy (%)· Extra Data· 2022-09-28
CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention Code
#6PointCLIPSOTA
15.4
Accuracy (%)· Extra Data· 2021-12-04
PointCLIP: Point Cloud Understanding by CLIP Code