KAN or MLP? Point Cloud Shows the Way Forward

• URL: http://arxiv.org/abs/2504.13593v1
• Date: Fri, 18 Apr 2025 09:52:22 GMT
• Title: KAN or MLP? Point Cloud Shows the Way Forward
• Authors: Yan Shi, Qingdong He, Yijun Liu, Xiaoyu Liu, Jingyong Su,
• Abstract summary: We propose PointKAN, which applies Kolmogorov-Arnold Learning Networks (KANs) to point cloud analysis tasks.<n>We show that PointKAN outperforms PointMLP on benchmark datasets such as ModelNet40, ScanNN, and ShapeNetPart.<n>This work highlights the potential of KANs-based architectures in 3D vision and opens new avenues for research in point cloud understanding.
• Score: 13.669234791655075
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-Layer Perceptrons (MLPs) have become one of the fundamental architectural component in point cloud analysis due to its effective feature learning mechanism. However, when processing complex geometric structures in point clouds, MLPs' fixed activation functions struggle to efficiently capture local geometric features, while suffering from poor parameter efficiency and high model redundancy. In this paper, we propose PointKAN, which applies Kolmogorov-Arnold Networks (KANs) to point cloud analysis tasks to investigate their efficacy in hierarchical feature representation. First, we introduce a Geometric Affine Module (GAM) to transform local features, improving the model's robustness to geometric variations. Next, in the Local Feature Processing (LFP), a parallel structure extracts both group-level features and global context, providing a rich representation of both fine details and overall structure. Finally, these features are combined and processed in the Global Feature Processing (GFP). By repeating these operations, the receptive field gradually expands, enabling the model to capture complete geometric information of the point cloud. To overcome the high parameter counts and computational inefficiency of standard KANs, we develop Efficient-KANs in the PointKAN-elite variant, which significantly reduces parameters while maintaining accuracy. Experimental results demonstrate that PointKAN outperforms PointMLP on benchmark datasets such as ModelNet40, ScanObjectNN, and ShapeNetPart, with particularly strong performance in Few-shot Learning task. Additionally, PointKAN achieves substantial reductions in parameter counts and computational complexity (FLOPs). This work highlights the potential of KANs-based architectures in 3D vision and opens new avenues for research in point cloud understanding.

Related papers

• Point Cloud Understanding via Attention-Driven Contrastive Learning [64.65145700121442]
  Transformer-based models have advanced point cloud understanding by leveraging self-attention mechanisms. PointACL is an attention-driven contrastive learning framework designed to address these limitations. Our method employs an attention-driven dynamic masking strategy that guides the model to focus on under-attended regions.
  arXiv  Detail & Related papers  (2024-11-22T05:41:00Z)
• PointNet with KAN versus PointNet with MLP for 3D Classification and Segmentation of Point Sets [1.90365714903665]
  Kolmogorov-Arnold Networks (KANs) have recently gained attention as an alternative to traditional Multilayer Perceptrons (MLPs) in deep learning frameworks.<n>We introduce PointNet-KAN, which employs KANs instead of traditional networks.<n>We evaluate PointNet-KAN across various degrees and special types such as the Lagrange, Chebyshev, and Gegenbauers.
  arXiv  Detail & Related papers  (2024-10-14T01:57:06Z)
• DV-Matcher: Deformation-based Non-Rigid Point Cloud Matching Guided by Pre-trained Visual Features [1.3030624795284795]
  We present DV-Matcher, a learning-based framework for estimating dense correspondences between non-rigidly deformable point clouds.<n> Experimental results show that our method achieves state-of-the-art results in matching non-rigid point clouds in both near-isometric and heterogeneous shape collection.
  arXiv  Detail & Related papers  (2024-08-16T07:02:19Z)
• Point Tree Transformer for Point Cloud Registration [33.00645881490638]
  Point cloud registration is a fundamental task in the fields of computer vision and robotics. We propose a novel transformer-based approach for point cloud registration that efficiently extracts comprehensive local and global features. Our method achieves superior performance over the state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-06-25T13:14:26Z)
• PointMamba: A Simple State Space Model for Point Cloud Analysis [65.59944745840866]
  We propose PointMamba, transferring the success of Mamba, a recent representative state space model (SSM), from NLP to point cloud analysis tasks. Unlike traditional Transformers, PointMamba employs a linear complexity algorithm, presenting global modeling capacity while significantly reducing computational costs.
  arXiv  Detail & Related papers  (2024-02-16T14:56:13Z)
• PointGL: A Simple Global-Local Framework for Efficient Point Cloud Analysis [19.163081544030547]
  We introduce a novel, uncomplicated yet potent architecture known as PointGL to facilitate efficient point cloud analysis. The fusion of one-time point embedding and parameter-free graph pooling contributes to PointGL's defining attributes of minimized model complexity and heightened efficiency. Our PointGL attains state-of-the-art accuracy on the ScanObjectNN dataset while exhibiting a runtime that is more than 5 times faster and utilizing only approximately 4% of the FLOPs and 30% of the parameters compared to the recent PointMLP model.
  arXiv  Detail & Related papers  (2024-01-22T02:05:33Z)
• Point Deformable Network with Enhanced Normal Embedding for Point Cloud Analysis [59.12922158979068]
  Recently-based methods have shown strong performance in point cloud analysis. Simple architectures are able to learn geometric features in local point groups yet fail to model long-range dependencies directly. We propose Point Deformable Network (PDNet) to capture long-range relations with strong representation ability.
  arXiv  Detail & Related papers  (2023-12-20T14:52:07Z)
• PointeNet: A Lightweight Framework for Effective and Efficient Point Cloud Analysis [28.54939134635978]
  PointeNet is a network designed specifically for point cloud analysis. Our method demonstrates flexibility by seamlessly integrating with a classification/segmentation head or embedding into off-the-shelf 3D object detection networks. Experiments on object-level datasets, including ModelNet40, ScanObjectNN, ShapeNet KITTI, and the scene-level dataset KITTI, demonstrate the superior performance of PointeNet over state-of-the-art methods in point cloud analysis.
  arXiv  Detail & Related papers  (2023-12-20T03:34:48Z)
• Human as Points: Explicit Point-based 3D Human Reconstruction from Single-view RGB Images [71.91424164693422]
  We introduce an explicit point-based human reconstruction framework called HaP.<n>Our approach is featured by fully-explicit point cloud estimation, manipulation, generation, and refinement in the 3D geometric space.<n>Our results may indicate a paradigm rollback to the fully-explicit and geometry-centric algorithm design.
  arXiv  Detail & Related papers  (2023-11-06T05:52:29Z)
• Bidirectional Knowledge Reconfiguration for Lightweight Point Cloud Analysis [74.00441177577295]
  Point cloud analysis faces computational system overhead, limiting its application on mobile or edge devices. This paper explores feature distillation for lightweight point cloud models. We propose bidirectional knowledge reconfiguration to distill informative contextual knowledge from the teacher to the student.
  arXiv  Detail & Related papers  (2023-10-08T11:32:50Z)
• FatNet: A Feature-attentive Network for 3D Point Cloud Processing [1.502579291513768]
  We introduce a novel feature-attentive neural network layer, a FAT layer, that combines both global point-based features and local edge-based features in order to generate better embeddings. Our architecture achieves state-of-the-art results on the task of point cloud classification, as demonstrated on the ModelNet40 dataset.
  arXiv  Detail & Related papers  (2021-04-07T23:13:56Z)
• SoftPoolNet: Shape Descriptor for Point Cloud Completion and Classification [93.54286830844134]
  We propose a method for 3D object completion and classification based on point clouds. For the decoder stage, we propose regional convolutions, a novel operator aimed at maximizing the global activation entropy. We evaluate our approach on different 3D tasks such as object completion and classification, achieving state-of-the-art accuracy.
  arXiv  Detail & Related papers  (2020-08-17T14:32:35Z)
• Local Grid Rendering Networks for 3D Object Detection in Point Clouds [98.02655863113154]
  CNNs are powerful but it would be computationally costly to directly apply convolutions on point data after voxelizing the entire point clouds to a dense regular 3D grid. We propose a novel and principled Local Grid Rendering (LGR) operation to render the small neighborhood of a subset of input points into a low-resolution 3D grid independently. We validate LGR-Net for 3D object detection on the challenging ScanNet and SUN RGB-D datasets.
  arXiv  Detail & Related papers  (2020-07-04T13:57:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.