Papers › Point-PlaneNet: Plane kernel based convolutional neural network for point clouds analysis
Point-PlaneNet: Plane kernel based convolutional neural network for point clouds analysis
S.M. Moein Peyghambarzadeh, Fatemeh Azizmalayeri, Hassan Khotanlou, Amir Salarpour
Point cloud is accepted as an adequate representation for 3D data and most 3D sensors have the ability to generate this data. Due to point cloud's irregular format, analyzing this data using deep learning algorithms is quite challenging. In this paper, a new convolutional neural network, called Point-PlaneNet, is proposed that uses the concept of the distance between points and planes in order to exploit spatial local correlations. In the proposed method an alternative simple local operation, called PlaneConv, is introduced which can extract local geometric features from point clouds by learning a set of planes in Rn space. Our network takes raw point clouds as input and therefore avoids the need to transform point clouds to images or volumes. PlaneConv has a simple theoretical analysis and is easy to incorporate into deep learning models to improve their performance. In order to evaluate the proposed method for classification, part segmentation and scene semantic segmentation tasks, it has been applied on four Datasets: ModelNet-40, MNIST, ShapeNet-Part and S3DIS. The experimental results show the acceptable performance of the proposed method compared to previous approaches in all tasks.
Code
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.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| 3D Part Segmentation | ShapeNet-Part | Point-PlaneNet | Class Average IoU | 82.5 | #53 of 67 | Archive leaderboard | report |
| 3D Part Segmentation | ShapeNet-Part | Point-PlaneNet | Instance Average IoU | 85.1 | #53 of 67 | Archive leaderboard | report |
| 3D Point Cloud Classification | ModelNet40 | Point-PlaneNet | Mean Accuracy | 90.5 | #92 of 111 | Archive leaderboard | report |
| 3D Point Cloud Classification | ModelNet40 | Point-PlaneNet | Overall Accuracy | 92.1 | #92 of 111 | Archive leaderboard | report |
| Semantic Segmentation | S3DIS | Point-PlaneNet | Mean IoU | 54.8 | #48 of 54 | Archive leaderboard | report |
| Semantic Segmentation | S3DIS | Point-PlaneNet | Number of params | N/A | #48 of 54 | Archive leaderboard | report |
| Semantic Segmentation | S3DIS | Point-PlaneNet | oAcc | 83.9 | #48 of 54 | Archive leaderboard | report |
| Semantic Segmentation | ShapeNet | Point-PlaneNet | Mean IoU | 85.1 | #4 of 5 | 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