Spatial Transformer Point Convolution

• URL: http://arxiv.org/abs/2009.01427v1
• Date: Thu, 3 Sep 2020 03:12:25 GMT
• Title: Spatial Transformer Point Convolution
• Authors: Yuan Fang, Chunyan Xu, Zhen Cui, Yuan Zong, and Jian Yang
• Abstract summary: 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.
• Score: 47.993153127099895
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Point clouds are unstructured and unordered in the embedded 3D space. In order to produce consistent responses under different permutation layouts, most existing methods aggregate local spatial points through maximum or summation operation. But such an aggregation essentially belongs to the isotropic filtering on all operated points therein, which tends to lose the information of geometric structures. In this paper, 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 to learn those latent geometric components. To better encode unordered neighbor points, we design sparse deformer to transform them into the canonical ordered dictionary space by using direction dictionary learning. In the transformed space, the standard image-like convolution can be leveraged to generate anisotropic filtering, which is more robust to express those finer variances of local regions. Dictionary learning and encoding processes are encapsulated into a network module and jointly learnt in an end-to-end manner. Extensive experiments on several public datasets (including S3DIS, Semantic3D, SemanticKITTI) demonstrate the effectiveness of our proposed method in point clouds semantic segmentation task.

Related papers

• Learning SO(3)-Invariant Semantic Correspondence via Local Shape Transform [62.27337227010514]
  We introduce a novel self-supervised Rotation-Invariant 3D correspondence learner with Local Shape Transform, dubbed RIST. RIST learns to establish dense correspondences between shapes even under challenging intra-class variations and arbitrary orientations. RIST demonstrates state-of-the-art performances on 3D part label transfer and semantic keypoint transfer given arbitrarily rotated point cloud pairs.
  arXiv  Detail & Related papers  (2024-04-17T08:09:25Z)
• Rethinking Rotation Invariance with Point Cloud Registration [18.829454172955202]
  We propose an effective framework for rotation invariance learning via three sequential stages, namely rotation-invariant shape encoding, aligned feature integration, and deep feature registration. Experimental results on 3D shape classification, part segmentation, and retrieval tasks prove the feasibility of our work.
  arXiv  Detail & Related papers  (2022-12-31T08:17:09Z)
• Dynamic Convolution for 3D Point Cloud Instance Segmentation [146.7971476424351]
  We propose an approach to instance segmentation from 3D point clouds based on dynamic convolution. We gather homogeneous points that have identical semantic categories and close votes for the geometric centroids. The proposed approach is proposal-free, and instead exploits a convolution process that adapts to the spatial and semantic characteristics of each instance.
  arXiv  Detail & Related papers  (2021-07-18T09:05:16Z)
• Permutation Matters: Anisotropic Convolutional Layer for Learning on Point Clouds [145.79324955896845]
  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.
  arXiv  Detail & Related papers  (2020-05-27T02:42:29Z)
• 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)
• Quaternion Equivariant Capsule Networks for 3D Point Clouds [58.566467950463306]
  We present a 3D capsule module for processing point clouds that is equivariant to 3D rotations and translations. We connect dynamic routing between capsules to the well-known Weiszfeld algorithm. Based on our operator, we build a capsule network that disentangles geometry from pose.
  arXiv  Detail & Related papers  (2019-12-27T13:51:17Z)

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.