Global Hierarchical Attention for 3D Point Cloud Analysis
- URL: http://arxiv.org/abs/2208.03791v1
- Date: Sun, 7 Aug 2022 19:16:30 GMT
- Title: Global Hierarchical Attention for 3D Point Cloud Analysis
- Authors: Dan Jia and Alexander Hermans and Bastian Leibe
- Abstract summary: We propose a new attention mechanism, called Global Hierarchical Attention (GHA) for 3D point cloud analysis.
For the task of semantic segmentation, GHA gives a +1.7% mIoU increase to the MinkowskiEngine baseline on ScanNet.
For the 3D object detection task, GHA improves the CenterPoint baseline by +0.5% mAP on the nuScenes dataset.
- Score: 88.56041763189162
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We propose a new attention mechanism, called Global Hierarchical Attention
(GHA), for 3D point cloud analysis. GHA approximates the regular global
dot-product attention via a series of coarsening and interpolation operations
over multiple hierarchy levels. The advantage of GHA is two-fold. First, it has
linear complexity with respect to the number of points, enabling the processing
of large point clouds. Second, GHA inherently possesses the inductive bias to
focus on spatially close points, while retaining the global connectivity among
all points. Combined with a feedforward network, GHA can be inserted into many
existing network architectures. We experiment with multiple baseline networks
and show that adding GHA consistently improves performance across different
tasks and datasets. For the task of semantic segmentation, GHA gives a +1.7%
mIoU increase to the MinkowskiEngine baseline on ScanNet. For the 3D object
detection task, GHA improves the CenterPoint baseline by +0.5% mAP on the
nuScenes dataset, and the 3DETR baseline by +2.1% mAP25 and +1.5% mAP50 on
ScanNet.
Related papers
- Clustering based Point Cloud Representation Learning for 3D Analysis [80.88995099442374]
We propose a clustering based supervised learning scheme for point cloud analysis.
Unlike current de-facto, scene-wise training paradigm, our algorithm conducts within-class clustering on the point embedding space.
Our algorithm shows notable improvements on famous point cloud segmentation datasets.
arXiv Detail & Related papers (2023-07-27T03:42:12Z) - EGRC-Net: Embedding-induced Graph Refinement Clustering Network [66.44293190793294]
We propose a novel graph clustering network called Embedding-Induced Graph Refinement Clustering Network (EGRC-Net)
EGRC-Net effectively utilizes the learned embedding to adaptively refine the initial graph and enhance the clustering performance.
Our proposed methods consistently outperform several state-of-the-art approaches.
arXiv Detail & Related papers (2022-11-19T09:08:43Z) - HPGNN: Using Hierarchical Graph Neural Networks for Outdoor Point Cloud
Processing [0.7649716717097428]
Motivated by recent improvements in point cloud processing for autonomous navigation, we focus on using hierarchical graph neural networks for processing.
We propose Hierarchical Point Graph Neural Network (HPGNN)
It learns node features at various levels of graph coarseness to extract information.
This enables to learn over a large point cloud while retaining fine details that existing point-level graph networks struggle to achieve.
arXiv Detail & Related papers (2022-06-05T11:18:09Z) - APP-Net: Auxiliary-point-based Push and Pull Operations for Efficient
Point Cloud Classification [48.230170172837084]
Point-cloud-based 3D classification task involves aggregating features from neighbor points.
To address these issues, we propose a new local aggregator of linear complexity, coined as APP.
We use an online normal estimation module to provide the explainable geometric information to enhance our APP modeling capability.
arXiv Detail & Related papers (2022-05-02T12:21:11Z) - MVP-Net: Multiple View Pointwise Semantic Segmentation of Large-Scale
Point Clouds [13.260488842875649]
In this paper, we propose an end-to-end neural architecture, Multiple View Pointwise Net, MVP-Net, to efficiently infer large-scale outdoor point cloud without KNN or complex pre/postprocessing.
Numerical experiments show that the proposed MVP-Net is 11 times faster than the most efficient pointwise semantic segmentation method RandLA-Net.
arXiv Detail & Related papers (2022-01-30T09:43:00Z) - Background-Aware 3D Point Cloud Segmentationwith Dynamic Point Feature
Aggregation [12.093182949686781]
We propose a novel 3D point cloud learning network, referred to as Dynamic Point Feature Aggregation Network (DPFA-Net)
DPFA-Net has two variants for semantic segmentation and classification of 3D point clouds.
It achieves the state-of-the-art overall accuracy score for semantic segmentation on the S3DIS dataset.
arXiv Detail & Related papers (2021-11-14T05:46:05Z) - FatNet: A Feature-attentive Network for 3D Point Cloud Processing [1.502579291513768]
We introduce a novel feature-attentive neural network layer, a FAT layer, that combines both global point-based features and local edge-based features in order to generate better embeddings.
Our architecture achieves state-of-the-art results on the task of point cloud classification, as demonstrated on the ModelNet40 dataset.
arXiv Detail & Related papers (2021-04-07T23:13:56Z) - PIG-Net: Inception based Deep Learning Architecture for 3D Point Cloud
Segmentation [0.9137554315375922]
We propose a inception based deep network architecture called PIG-Net, that effectively characterizes the local and global geometric details of the point clouds.
We perform an exhaustive experimental analysis of the PIG-Net architecture on two state-of-the-art datasets.
arXiv Detail & Related papers (2021-01-28T13:27:55Z) - PC-RGNN: Point Cloud Completion and Graph Neural Network for 3D Object
Detection [57.49788100647103]
LiDAR-based 3D object detection is an important task for autonomous driving.
Current approaches suffer from sparse and partial point clouds of distant and occluded objects.
In this paper, we propose a novel two-stage approach, namely PC-RGNN, dealing with such challenges by two specific solutions.
arXiv Detail & Related papers (2020-12-18T18:06:43Z) - PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation [111.7241018610573]
We present PointGroup, a new end-to-end bottom-up architecture for instance segmentation.
We design a two-branch network to extract point features and predict semantic labels and offsets, for shifting each point towards its respective instance centroid.
A clustering component is followed to utilize both the original and offset-shifted point coordinate sets, taking advantage of their complementary strength.
We conduct extensive experiments on two challenging datasets, ScanNet v2 and S3DIS, on which our method achieves the highest performance, 63.6% and 64.0%, compared to 54.9% and 54.4% achieved by former best
arXiv Detail & Related papers (2020-04-03T16:26:37Z)
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.