Permutation Matters: Anisotropic Convolutional Layer for Learning on Point Clouds

• URL: http://arxiv.org/abs/2005.13135v2
• Date: Fri, 5 Jun 2020 16:32:43 GMT
• Title: Permutation Matters: Anisotropic Convolutional Layer for Learning on Point Clouds
• Authors: Zhongpai Gao, Guangtao Zhai, Junchi Yan, Xiaokang Yang
• Abstract summary: We propose a permutable anisotropic convolutional operation (PAI-Conv) that calculates soft-permutation matrices for each point. Experiments on point clouds demonstrate that PAI-Conv produces competitive results in classification and semantic segmentation tasks.
• Score: 145.79324955896845
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: It has witnessed a growing demand for efficient representation learning on point clouds in many 3D computer vision applications. Behind the success story of convolutional neural networks (CNNs) is that the data (e.g., images) are Euclidean structured. However, point clouds are irregular and unordered. Various point neural networks have been developed with isotropic filters or using weighting matrices to overcome the structure inconsistency on point clouds. However, isotropic filters or weighting matrices limit the representation power. In this paper, we propose a permutable anisotropic convolutional operation (PAI-Conv) that calculates soft-permutation matrices for each point using dot-product attention according to a set of evenly distributed kernel points on a sphere's surface and performs shared anisotropic filters. In fact, dot product with kernel points is by analogy with the dot-product with keys in Transformer as widely used in natural language processing (NLP). From this perspective, PAI-Conv can be regarded as the transformer for point clouds, which is physically meaningful and is robust to cooperate with the efficient random point sampling method. Comprehensive experiments on point clouds demonstrate that PAI-Conv produces competitive results in classification and semantic segmentation tasks compared to state-of-the-art methods.

Related papers

• BiEquiFormer: Bi-Equivariant Representations for Global Point Cloud Registration [28.75341781515012]
  The goal of this paper is to address the problem of global point cloud registration (PCR) i.e., finding the optimal alignment between point clouds. We show that state-of-the-art deep learning methods suffer from huge performance degradation when the point clouds are arbitrarily placed in space.
  arXiv  Detail & Related papers  (2024-07-11T17:58:10Z)
• Learning Neural Volumetric Field for Point Cloud Geometry Compression [13.691147541041804]
  We propose to code the geometry of a given point cloud by learning a neural field. We divide the entire space into small cubes and represent each non-empty cube by a neural network and an input latent code. The network is shared among all the cubes in a single frame or multiple frames, to exploit the spatial and temporal redundancy.
  arXiv  Detail & Related papers  (2022-12-11T19:55:24Z)
• Self-Supervised Arbitrary-Scale Point Clouds Upsampling via Implicit Neural Representation [79.60988242843437]
  We propose a novel approach that achieves self-supervised and magnification-flexible point clouds upsampling simultaneously. Experimental results demonstrate that our self-supervised learning based scheme achieves competitive or even better performance than supervised learning based state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-04-18T07:18:25Z)
• Differentiable Convolution Search for Point Cloud Processing [114.66038862207118]
  We propose a novel differential convolution search paradigm on point clouds. It can work in a purely data-driven manner and thus is capable of auto-creating a group of suitable convolutions for geometric shape modeling. We also propose a joint optimization framework for simultaneous search of internal convolution and external architecture, and introduce epsilon-greedy algorithm to alleviate the effect of discretization error.
  arXiv  Detail & Related papers  (2021-08-29T14:42:03Z)
• Adaptive Graph Convolution for Point Cloud Analysis [25.175406613705274]
  We propose Adaptive Graph Convolution (AdaptConv) which generates adaptive kernels for points according to their dynamically learned features. Our method outperforms state-of-the-art point cloud classification and segmentation approaches on several benchmark datasets.
  arXiv  Detail & Related papers  (2021-08-18T08:38:52Z)
• PU-Flow: a Point Cloud Upsampling Networkwith Normalizing Flows [58.96306192736593]
  We present PU-Flow, which incorporates normalizing flows and feature techniques to produce dense points uniformly distributed on the underlying surface. Specifically, we formulate the upsampling process as point in a latent space, where the weights are adaptively learned from local geometric context. We show that our method outperforms state-of-the-art deep learning-based approaches in terms of reconstruction quality, proximity-to-surface accuracy, and computation efficiency.
  arXiv  Detail & Related papers  (2021-07-13T07:45:48Z)
• PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds [33.41204351513122]
  PAConv is a generic convolution operation for 3D point cloud processing. The kernel is built in a data-driven manner, endowing PAConv with more flexibility than 2D convolutions. Even built on simple networks, our method still approaches or even surpasses the state-of-the-art models.
  arXiv  Detail & Related papers  (2021-03-26T17:52:38Z)
• Pct: Point cloud transformer [35.34343810480954]
  This paper presents a novel framework named Point Cloud Transformer for point cloud learning. PCT is based on Transformer, which achieves huge success in natural language processing. It is inherently permutation invariant for processing a sequence of points, making it well-suited for point cloud learning.
  arXiv  Detail & Related papers  (2020-12-17T15:55:17Z)
• Spatial Transformer Point Convolution [47.993153127099895]
  We propose a spatial transformer point convolution (STPC) method to achieve anisotropic convolution filtering on point clouds. To capture and represent implicit geometric structures, we specifically introduce spatial direction dictionary. In the transformed space, the standard image-like convolution can be leveraged to generate anisotropic filtering.
  arXiv  Detail & Related papers  (2020-09-03T03:12:25Z)
• Learning Local Neighboring Structure for Robust 3D Shape Representation [143.15904669246697]
  Representation learning for 3D meshes is important in many computer vision and graphics applications. We propose a local structure-aware anisotropic convolutional operation (LSA-Conv) Our model produces significant improvement in 3D shape reconstruction compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-04-21T13:40:03Z)

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.