Enhancing Local Geometry Learning for 3D Point Cloud via Decoupling Convolution

• URL: http://arxiv.org/abs/2207.01181v1
• Date: Mon, 4 Jul 2022 03:49:13 GMT
• Title: Enhancing Local Geometry Learning for 3D Point Cloud via Decoupling Convolution
• Authors: Haoyi Xiu, Xin Liu, Weimin Wang, Kyoung-Sook Kim, Takayuki Shinohara, Qiong Chang, Masashi Matsuoka
• Abstract summary: We propose Laplacian Unit (LU) as a simple yet effective architectural unit that can enhance the learning of local geometry. LU achieves competitive or superior performance on typical point cloud understanding tasks.
• Score: 10.449455311881398
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modeling the local surface geometry is challenging in 3D point cloud understanding due to the lack of connectivity information. Most prior works model local geometry using various convolution operations. We observe that the convolution can be equivalently decomposed as a weighted combination of a local and a global component. With this observation, we explicitly decouple these two components so that the local one can be enhanced and facilitate the learning of local surface geometry. Specifically, we propose Laplacian Unit (LU), a simple yet effective architectural unit that can enhance the learning of local geometry. Extensive experiments demonstrate that networks equipped with LUs achieve competitive or superior performance on typical point cloud understanding tasks. Moreover, through establishing connections between the mean curvature flow, a further investigation of LU based on curvatures is made to interpret the adaptive smoothing and sharpening effect of LU. The code will be available.

Related papers

• Boosting Cross-Domain Point Classification via Distilling Relational Priors from 2D Transformers [59.0181939916084]
  Traditional 3D networks mainly focus on local geometric details and ignore the topological structure between local geometries. We propose a novel Priors Distillation (RPD) method to extract priors from the well-trained transformers on massive images. Experiments on the PointDA-10 and the Sim-to-Real datasets verify that the proposed method consistently achieves the state-of-the-art performance of UDA for point cloud classification.
  arXiv  Detail & Related papers  (2024-07-26T06:29:09Z)
• 3D Geometric Shape Assembly via Efficient Point Cloud Matching [59.241448711254485]
  We introduce Proxy Match Transform (PMT), an approximate high-order feature transform layer that enables reliable matching between mating surfaces of parts. Building upon PMT, we introduce a new framework, dubbed Proxy Match TransformeR (PMTR), for the geometric assembly task. We evaluate the proposed PMTR on the large-scale 3D geometric shape assembly benchmark dataset of Breaking Bad.
  arXiv  Detail & Related papers  (2024-07-15T08:50:02Z)
• LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformers [60.51925353387151]
  We propose a novel module named Local Context Propagation (LCP) to exploit the message passing between neighboring local regions. We use the overlap points of adjacent local regions as intermediaries, then re-weight the features of these shared points from different local regions before passing them to the next layers. The proposed method is applicable to different tasks and outperforms various transformer-based methods in benchmarks including 3D shape classification and dense prediction tasks.
  arXiv  Detail & Related papers  (2022-10-23T15:43:01Z)
• Neural Convolutional Surfaces [59.172308741945336]
  This work is concerned with a representation of shapes that disentangles fine, local and possibly repeating geometry, from global, coarse structures. We show that this approach achieves better neural shape compression than the state of the art, as well as enabling manipulation and transfer of shape details.
  arXiv  Detail & Related papers  (2022-04-05T15:40:11Z)
• Depth Completion using Geometry-Aware Embedding [22.333381291860498]
  This paper proposes an efficient method to learn geometry-aware embedding. It encodes the local and global geometric structure information from 3D points, e.g., scene layout, object's sizes and shapes, to guide dense depth estimation.
  arXiv  Detail & Related papers  (2022-03-21T12:06:27Z)
• RIConv++: Effective Rotation Invariant Convolutions for 3D Point Clouds Deep Learning [32.18566879365623]
  3D point clouds deep learning is a promising field of research that allows a neural network to learn features of point clouds directly. We propose a simple yet effective convolution operator that enhances feature distinction by designing powerful rotation invariant features from the local regions. Our network architecture can capture both local and global context by simply tuning the neighborhood size in each convolution layer.
  arXiv  Detail & Related papers  (2022-02-26T08:32:44Z)
• DeltaConv: Anisotropic Point Cloud Learning with Exterior Calculus [13.18401177210079]
  We introduce a new convolution operator called DeltaConv, which combines geometric operators from exterior calculus to enable the construction of anisotropic filters on point clouds. Our convolutions are robust and simple to implement and show improved accuracy compared to state-of-the-art approaches on several benchmarks.
  arXiv  Detail & Related papers  (2021-11-16T21:58:55Z)
• Deep Implicit Moving Least-Squares Functions for 3D Reconstruction [23.8586965588835]
  In this work, we turn the discrete point sets into smooth surfaces by introducing the well-known implicit moving least-squares (IMLS) surface formulation. We incorporate IMLS surface generation into deep neural networks for inheriting both the flexibility of point sets and the high quality of implicit surfaces. Our experiments on 3D object reconstruction demonstrate that IMLSNets outperform state-of-the-art learning-based methods in terms of reconstruction quality and computational efficiency.
  arXiv  Detail & Related papers  (2021-03-23T02:26:07Z)
• Concentric Spherical GNN for 3D Representation Learning [53.45704095146161]
  We propose a novel multi-resolution convolutional architecture for learning over concentric spherical feature maps. Our hierarchical architecture is based on alternatively learning to incorporate both intra-sphere and inter-sphere information. We demonstrate the effectiveness of our approach in improving state-of-the-art performance on 3D classification tasks with rotated data.
  arXiv  Detail & Related papers  (2021-03-18T19:05:04Z)
• A Rotation-Invariant Framework for Deep Point Cloud Analysis [132.91915346157018]
  We introduce a new low-level purely rotation-invariant representation to replace common 3D Cartesian coordinates as the network inputs. Also, we present a network architecture to embed these representations into features, encoding local relations between points and their neighbors, and the global shape structure. We evaluate our method on multiple point cloud analysis tasks, including shape classification, part segmentation, and shape retrieval.
  arXiv  Detail & Related papers  (2020-03-16T14:04:45Z)

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.