PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds

• URL: http://arxiv.org/abs/2103.14635v1
• Date: Fri, 26 Mar 2021 17:52:38 GMT
• Title: PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds
• Authors: Mutian Xu, Runyu Ding, Hengshuang Zhao, Xiaojuan Qi
• Abstract summary: 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.
• Score: 33.41204351513122
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We introduce Position Adaptive Convolution (PAConv), a generic convolution operation for 3D point cloud processing. The key of PAConv is to construct the convolution kernel by dynamically assembling basic weight matrices stored in Weight Bank, where the coefficients of these weight matrices are self-adaptively learned from point positions through ScoreNet. In this way, the kernel is built in a data-driven manner, endowing PAConv with more flexibility than 2D convolutions to better handle the irregular and unordered point cloud data. Besides, the complexity of the learning process is reduced by combining weight matrices instead of brutally predicting kernels from point positions. Furthermore, different from the existing point convolution operators whose network architectures are often heavily engineered, we integrate our PAConv into classical MLP-based point cloud pipelines without changing network configurations. Even built on simple networks, our method still approaches or even surpasses the state-of-the-art models, and significantly improves baseline performance on both classification and segmentation tasks, yet with decent efficiency. Thorough ablation studies and visualizations are provided to understand PAConv. Code is released on https://github.com/CVMI Lab/PAConv.

Related papers

• Omni-Dimensional Dynamic Convolution [25.78940854339179]
  Learning a single static convolutional kernel in each convolutional layer is the common training paradigm of modern Convolutional Neural Networks (CNNs) Recent research in dynamic convolution shows that learning a linear combination of $n$ convolutional kernels weighted with their input-dependent attentions can significantly improve the accuracy of light-weight CNNs. We present Omni-dimensional Dynamic Convolution (ODConv), a more generalized yet elegant dynamic convolution design.
  arXiv  Detail & Related papers  (2022-09-16T14:05:38Z)
• Focal Sparse Convolutional Networks for 3D Object Detection [121.45950754511021]
  We introduce two new modules to enhance the capability of Sparse CNNs. They are focal sparse convolution (Focals Conv) and its multi-modal variant of focal sparse convolution with fusion. For the first time, we show that spatially learnable sparsity in sparse convolution is essential for sophisticated 3D object detection.
  arXiv  Detail & Related papers  (2022-04-26T17:34:10Z)
• DFC: Deep Feature Consistency for Robust Point Cloud Registration [0.4724825031148411]
  We present a novel learning-based alignment network for complex alignment scenes. We validate our approach on the 3DMatch dataset and the KITTI odometry dataset.
  arXiv  Detail & Related papers  (2021-11-15T08:27:21Z)
• 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)
• 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)
• DV-ConvNet: Fully Convolutional Deep Learning on Point Clouds with Dynamic Voxelization and 3D Group Convolution [0.7340017786387767]
  3D point cloud interpretation is a challenging task due to the randomness and sparsity of the component points. In this work, we draw attention back to the standard 3D convolutions towards an efficient 3D point cloud interpretation. Our network is able to run and converge at a considerably fast speed, while yields on-par or even better performance compared with the state-of-the-art methods on several benchmark datasets.
  arXiv  Detail & Related papers  (2020-09-07T07:45:05Z)
• PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer [76.44375136492827]
  Convolutional Neural Networks (CNNs) are often scale-sensitive. We bridge this regret by exploiting multi-scale features in a finer granularity. The proposed convolution operation, named Poly-Scale Convolution (PSConv), mixes up a spectrum of dilation rates.
  arXiv  Detail & Related papers  (2020-07-13T05:14:11Z)
• 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)
• PointGMM: a Neural GMM Network for Point Clouds [83.9404865744028]
  Point clouds are popular representation for 3D shapes, but encode a particular sampling without accounting for shape priors or non-local information. We present PointGMM, a neural network that learns to generate hGMMs which are characteristic of the shape class. We show that as a generative model, PointGMM learns a meaningful latent space which enables generating consistents between existing shapes.
  arXiv  Detail & Related papers  (2020-03-30T10:34:59Z)

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.