Published on Sun Nov 08 2020

Point Transformer for Shape Classification and Retrieval of 3D and ALS Roof PointClouds

Dimple A Shajahan, Mukund Varma T, Ramanathan Muthuganapathy

This paper proposes a fully attentional model for deriving a rich point cloud representation. The model's shape classification and retrieval performance are evaluated on a large-scale urban dataset - RoofN3D and a standard benchmark dataset ModelNet40.

1
4
6
Abstract

The success of deep learning methods led to significant breakthroughs in 3-D point cloud processing tasks with applications in remote sensing. Existing methods utilize convolutions that have some limitations, as they assume a uniform input distribution and cannot learn long-range dependencies. Recent works have shown that adding attention in conjunction with these methods improves performance. This raises a question: can attention layers completely replace convolutions? This paper proposes a fully attentional model - {\em Point Transformer}, for deriving a rich point cloud representation. The model's shape classification and retrieval performance are evaluated on a large-scale urban dataset - RoofN3D and a standard benchmark dataset ModelNet40. Extensive experiments are conducted to test the model's robustness to unseen point corruptions for analyzing its effectiveness on real datasets. The proposed method outperforms other state-of-the-art models in the RoofN3D dataset, gives competitive results in the ModelNet40 benchmark, and showcases high robustness to various unseen point corruptions. Furthermore, the model is highly memory and space efficient when compared to other methods.

Fri Nov 01 2019
Computer Vision
Rotation Invariant Point Cloud Classification: Where Local Geometry Meets Global Topology
Point cloud analysis is a fundamental task in 3D computer vision. How to achieve rotation invariance remains an open problem in point cloud analysis. In our local-global-representation (LGR)-Net, we have designed a two-branch network.
1
0
0
Thu Dec 17 2020
Computer Vision
PCT: Point cloud transformer
The irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud processing. This paper presents a novel framework named Point Cloud Transformer(PCT) for point cloud learning. PCT is based on Transformer, which achieves huge success in natural language processing.
2
1
8
Tue Jun 01 2021
Computer Vision
VA-GCN: A Vector Attention Graph Convolution Network for learning on Point Clouds
The proposed VA-GCN achieves state-of-the-art performance on standard benchmarks including ModelNet40, S3DIS and ShapeNet. On the Model net40 dataset for 3D classification, VA- GCN increased by 2.4% compared to the baseline.
1
0
0
Fri Jun 25 2021
Computer Vision
"Zero Shot" Point Cloud Upsampling
Point cloud upsampling using deep learning has been paid various efforts in the past few years. We present an unsupervised approach to upsample point clouds internally referred as "Zero Shot" Point Cloud Upsampling (ZSPU) at aholistic level.
5
0
0
Fri Dec 27 2019
Computer Vision
Deep Learning for 3D Point Clouds: A Survey
Point cloud learning has lately attracted increasing attention due to its wide applications. This paper presents a comprehensive review of recent progress in deep learning methods for point clouds. It covers three major tasks, including 3Dshape classification, 3D object detection and tracking, and 3D point cloud segmentation.
1
0
0
Wed Jun 09 2021
Computer Vision
Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline
SimpleView outperforms state-of-the-art methods on ScanObjectNN, a real-world point cloud benchmark, and demonstrates better cross-dataset generalization.
1
5
15
Mon Jun 12 2017
NLP
Attention Is All You Need
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms. Experiments on two machine translation tasks show these models to be superior in
50
215
883
Fri Dec 02 2016
Computer Vision
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Point cloud is an important type of geometric data structure. Most researchers transform such data to regular 3D voxel grids or collections of images. This, however, renders data unnecessarily voluminous. In this paper, we design a novel type of neural network that directly consumes point clouds.
1
0
1
Wed Jun 07 2017
Computer Vision
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
Few prior works study deep learning on point sets. PointNet by Qi et al. is a pioneer in this direction. By exploiting metric space distances, our network is able to learn local features with progressivelyincreasing contextual scales.
0
0
0
Wed Dec 09 2015
Artificial Intelligence
ShapeNet: An Information-Rich 3D Model Repository
ShapeNet is a richly-annotated, large-scale repository of 3D CAD models of objects. At the time of this technical report, ShapeNet has indexed more than 3,000,000 models, 220,000 of which are classified into 3,135 categories.
0
0
0
Sun Jun 22 2014
Computer Vision
3D ShapeNets: A Deep Representation for Volumetric Shapes
3D shape is a crucial but heavily underutilized cue in today's computer vision systems. We propose to represent a geometric 3D shape as a probability distribution of binary variables on a 3D voxel grid.
0
0
0
Fri Aug 02 2019
Machine Learning
L2G Auto-encoder: Understanding Point Clouds by Local-to-Global Reconstruction with Hierarchical Self-Attention
Local-to-Global auto-encoder (L2G-AE) can simultaneously learn the local and global structure of point clouds by local to global shape reconstruction. L2 G-AE can understand point clouds better than state-of-the-art methods.
0
0
0