Papers › GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning

GPr-Net: Geometric Prototypical Network for Point Cloud Few-Shot Learning

12 Apr 2023arXiv:2304.06007archive 2025-07-28

Tejas Anvekar, Dena Bazazian

In the realm of 3D-computer vision applications, point cloud few-shot learning plays a critical role. However, it poses an arduous challenge due to the sparsity, irregularity, and unordered nature of the data. Current methods rely on complex local geometric extraction techniques such as convolution, graph, and attention mechanisms, along with extensive data-driven pre-training tasks. These approaches contradict the fundamental goal of few-shot learning, which is to facilitate efficient learning. To address this issue, we propose GPr-Net (Geometric Prototypical Network), a lightweight and computationally efficient geometric prototypical network that captures the intrinsic topology of point clouds and achieves superior performance. Our proposed method, IGI++ (Intrinsic Geometry Interpreter++) employs vector-based hand-crafted intrinsic geometry interpreters and Laplace vectors to extract and evaluate point cloud morphology, resulting in improved representations for FSL (Few-Shot Learning). Additionally, Laplace vectors enable the extraction of valuable features from point clouds with fewer points. To tackle the distribution drift challenge in few-shot metric learning, we leverage hyperbolic space and demonstrate that our approach handles intra and inter-class variance better than existing point cloud few-shot learning methods. Experimental results on the ModelNet40 dataset show that GPr-Net outperforms state-of-the-art methods in few-shot learning on point clouds, achieving utmost computational efficiency that is 170× better than all existing works. The code is publicly available at https://github.com/TejasAnvekar/GPr-Net.

PaperPDFCode

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

tejasanvekar/gpr-net officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Mix3D: Out-of-Context Data Augmentation for 3D Scenes (arXiv:2110.02210; that paper's own run record: 20 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 0 violated, 16 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
TejasAnvekar/Mahalanobis-k-NN mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Mix3D: Out-of-Context Data Augmentation for 3D Scenes (arXiv:2110.02210; that paper's own run record: 20 ran (of which 0 constructed an object rather than computing a result; 18 with no instrument failure: 2 honoured, 0 violated, 16 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Computational EfficiencyFew-Shot 3D Point Cloud ClassificationFew-Shot LearningGPRMetric Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) GPr-Net + Hyp (512) Overall Accuracy 71.6 #22 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) GPr-Net + Hyp (512) Standard Deviation 1.1 #22 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) GPr-Net + Hyp (1024) Overall Accuracy 70.4 #23 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) GPr-Net + Hyp (1024) Standard Deviation 1.8 #23 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) GPr-Net + Euc (512) Overall Accuracy 62.3 #24 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) GPr-Net + Euc (512) Standard Deviation 2.0 #24 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) GPr-Net + Euc (1024) Overall Accuracy 62.1 #25 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (10-shot) GPr-Net + Euc (1024) Standard Deviation 1.9 #25 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) GPr-Net + Hyp (512) Overall Accuracy 73.8 #22 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) GPr-Net + Hyp (512) Standard Deviation 2.0 #22 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) GPr-Net + Hyp (1024) Overall Accuracy 72.8 #23 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) GPr-Net + Hyp (1024) Standard Deviation 1.8 #23 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) GPr-Net + Euc (1024) Overall Accuracy 63.4 #24 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) GPr-Net + Euc (1024) Standard Deviation 2.0 #24 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) GPr-Net + Euc (512) Overall Accuracy 63.3 #25 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 10-way (20-shot) GPr-Net + Euc (512) Standard Deviation 2.2 #25 of 31 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) GPr-Net + Hyp (512) Overall Accuracy 81.1 #21 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) GPr-Net + Hyp (512) Standard Deviation 1.5 #21 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) GPr-Net + Hyp (1024) Overall Accuracy 80.4 #22 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) GPr-Net + Hyp (1024) Standard Deviation 0.5 #22 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) GPr-Net + Euc (1024) Overall Accuracy 74.4 #23 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) GPr-Net + Euc (1024) Standard Deviation 2.0 #23 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) GPr-Net + Euc (512) Overall Accuracy 74.0 #24 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (10-shot) GPr-Net + Euc (512) Standard Deviation 2.3 #24 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) GPr-Net + Hyp (512) Overall Accuracy 82.7 #21 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) GPr-Net + Hyp (512) Standard Deviation 1.3 #21 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) GPr-Net + Hyp (1024) Overall Accuracy 82.0 #22 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) GPr-Net + Hyp (1024) Standard Deviation 0.9 #22 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) GPr-Net + Euc (1024) Overall Accuracy 75.1 #23 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) GPr-Net + Euc (1024) Standard Deviation 2.1 #23 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) GPr-Net + Euc (512) Overall Accuracy 75.0 #24 of 30 Archive leaderboard report
Few-Shot 3D Point Cloud Classification ModelNet40 5-way (20-shot) GPr-Net + Euc (512) Standard Deviation 2.4 #24 of 30 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections