GASCN: Graph Attention Shape Completion Network
- URL: http://arxiv.org/abs/2201.07937v1
- Date: Thu, 20 Jan 2022 01:03:00 GMT
- Title: GASCN: Graph Attention Shape Completion Network
- Authors: Haojie Huang, Ziyi Yang, Robert Platt
- Abstract summary: Shape completion is the problem of inferring the complete geometry of an object given a partial point cloud.
This paper proposes the Graph Attention Shape Completion Network (GASCN), a novel neural network model that solves this problem.
For each completed point, our model infers the extent of the local surface patch which is used to produce dense yet precise shape completions.
- Score: 4.307812758854162
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Shape completion, the problem of inferring the complete geometry of an object
given a partial point cloud, is an important problem in robotics and computer
vision. This paper proposes the Graph Attention Shape Completion Network
(GASCN), a novel neural network model that solves this problem. This model
combines a graph-based model for encoding local point cloud information with an
MLP-based architecture for encoding global information. For each completed
point, our model infers the normal and extent of the local surface patch which
is used to produce dense yet precise shape completions. We report experiments
that demonstrate that GASCN outperforms standard shape completion methods on a
standard benchmark drawn from the Shapenet dataset.
Related papers
- Graph Auto-Encoders for Network Completion [6.1074304332419675]
We propose a model to use the learned pattern of connections from the observed part of the network to complete the whole graph.
Our proposed model achieved competitive performance with less information needed.
arXiv Detail & Related papers (2022-04-25T05:24:45Z) - PointAttN: You Only Need Attention for Point Cloud Completion [89.88766317412052]
Point cloud completion refers to completing 3D shapes from partial 3D point clouds.
We propose a novel neural network for processing point cloud in a per-point manner to eliminate kNNs.
The proposed framework, namely PointAttN, is simple, neat and effective, which can precisely capture the structural information of 3D shapes.
arXiv Detail & Related papers (2022-03-16T09:20:01Z) - Graph-Guided Deformation for Point Cloud Completion [35.10606375236494]
We propose a Graph-Guided Deformation Network, which respectively regards the input data and intermediate generation as controlling and supporting points.
Our key insight is to simulate the least square Laplacian deformation process via mesh deformation methods, which brings adaptivity for modeling variation in geometry details.
We are the first to refine the point cloud completion task by mimicing traditional graphics algorithms with GCN-guided deformation.
arXiv Detail & Related papers (2021-11-11T12:55:26Z) - Voxel-based Network for Shape Completion by Leveraging Edge Generation [76.23436070605348]
We develop a voxel-based network for point cloud completion by leveraging edge generation (VE-PCN)
We first embed point clouds into regular voxel grids, and then generate complete objects with the help of the hallucinated shape edges.
This decoupled architecture together with a multi-scale grid feature learning is able to generate more realistic on-surface details.
arXiv Detail & Related papers (2021-08-23T05:10:29Z) - ASFM-Net: Asymmetrical Siamese Feature Matching Network for Point
Completion [11.243242995190082]
We propose a novel point cloud completion network using a feature matching strategy, termed as ASFM-Net.
Specifically, the asymmetrical Siamese auto-encoder neural network is adopted to map the partial and complete input point cloud into a shared latent space, which can capture detailed shape prior.
Experiments are conducted on the PCN dataset and the Completion3D benchmark, demonstrating the state-of-the-art performance of the proposed ASFM-Net.
arXiv Detail & Related papers (2021-04-19T19:42:42Z) - PMP-Net: Point Cloud Completion by Learning Multi-step Point Moving
Paths [54.459879603473034]
We design a novel neural network, named PMP-Net, to mimic the behavior of an earth mover.
It moves each point of the incomplete input to complete the point cloud, where the total distance of point moving paths should be shortest.
It learns a strict and unique correspondence on point-level, which can capture the detailed topology and structure relationships between the incomplete shape and the complete target.
arXiv Detail & Related papers (2020-12-07T01:34:38Z) - Refinement of Predicted Missing Parts Enhance Point Cloud Completion [62.997667081978825]
Point cloud completion is the task of predicting complete geometry from partial observations using a point set representation for a 3D shape.
Previous approaches propose neural networks to directly estimate the whole point cloud through encoder-decoder models fed by the incomplete point set.
This paper proposes an end-to-end neural network architecture that focuses on computing the missing geometry and merging the known input and the predicted point cloud.
arXiv Detail & Related papers (2020-10-08T22:01:23Z) - GFPNet: A Deep Network for Learning Shape Completion in Generic Fitted
Primitives [68.8204255655161]
We propose an object reconstruction apparatus that uses the so-called Generic Primitives (GP) to complete shapes.
We show that GFPNet competes with state of the art shape completion methods by providing performance results on the ModelNet and KITTI benchmarking datasets.
arXiv Detail & Related papers (2020-06-03T08:29:27Z) - Point Cloud Completion by Skip-attention Network with Hierarchical
Folding [61.59710288271434]
We propose Skip-Attention Network (SA-Net) for 3D point cloud completion.
First, we propose a skip-attention mechanism to effectively exploit the local structure details of incomplete point clouds.
Second, in order to fully utilize the selected geometric information encoded by skip-attention mechanism at different resolutions, we propose a novel structure-preserving decoder.
arXiv Detail & Related papers (2020-05-08T06:23:51Z) - Airborne LiDAR Point Cloud Classification with Graph Attention
Convolution Neural Network [5.69168146446103]
We present a graph attention convolution neural network (GACNN) that can be directly applied to the classification of unstructured 3D point clouds obtained by airborne LiDAR.
Based on the proposed graph attention convolution module, we further design an end-to-end encoder-decoder network, named GACNN, to capture multiscale features of the point clouds.
Experiments on the ISPRS 3D labeling dataset show that the proposed model achieves a new state-of-the-art performance in terms of average F1 score (71.5%) and a satisfying overall accuracy (83.2%)
arXiv Detail & Related papers (2020-04-20T05:12:31Z)
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.