Related papers: Local Neighborhood Features for 3D Classification
Recently proposed neural network architectures like PointNet [QSMG16] and PointNet++ [QYSG17] have made it possible to apply Deep Learning to 3D point sets. The feature representations of shapes learned by these two networks enabled…
Over the last decade, the demand for better segmentation and classification algorithms in 3D spaces has significantly grown due to the popularity of new 3D sensor technologies and advancements in the field of robotics. Point-clouds are one…
Point clouds provide a compact and efficient representation of 3D shapes. While deep neural networks have achieved impressive results on point cloud learning tasks, they require massive amounts of manually labeled data, which can be costly…
As the basic task of point cloud analysis, classification is fundamental but always challenging. To address some unsolved problems of existing methods, we propose a network that captures geometric features of point clouds for better…
In this paper, we propose Attention Based Decomposition Network (ABD-Net), for point cloud decomposition into basic geometric shapes namely, plane, sphere, cone and cylinder. We show improved performance of 3D object classification using…
The 3D deep learning community has seen significant strides in pointcloud processing over the last few years. However, the datasets on which deep models have been trained have largely remained the same. Most datasets comprise clean,…
With deep learning becoming a more prominent approach for automatic classification of three-dimensional point cloud data, a key bottleneck is the amount of high quality training data, especially when compared to that available for…
Understanding dynamic 3D environment is crucial for robotic agents and many other applications. We propose a novel neural network architecture called $MeteorNet$ for learning representations for dynamic 3D point cloud sequences. Different…
This paper shows the effectiveness of 2D backbone scaling and pretraining for pillar-based 3D object detectors. Pillar-based methods mainly employ randomly initialized 2D convolution neural network (ConvNet) for feature extraction and fail…
Object point cloud classification has drawn great research attention since the release of benchmarking datasets, such as the ModelNet and the ShapeNet. These benchmarks assume point clouds covering complete surfaces of object instances, for…
3D point cloud analysis has drawn a lot of research attention due to its wide applications. However, collecting massive labelled 3D point cloud data is both time-consuming and labor-intensive. This calls for data-efficient learning methods.…
Although supervised deep normal estimators have recently shown impressive results on synthetic benchmarks, their performance deteriorates significantly in real-world scenarios due to the domain gap between synthetic and real data. Building…
This paper presents a neural network for robust normal estimation on point clouds, named AdaFit, that can deal with point clouds with noise and density variations. Existing works use a network to learn point-wise weights for weighted least…
In this paper, we present KeyMatchNet, a novel network for zero-shot pose estimation in 3D point clouds. Our method uses only depth information, making it more applicable for many industrial use cases, as color information is seldom…
We introduce Patch Refinement a two-stage model for accurate 3D object detection and localization from point cloud data. Patch Refinement is composed of two independently trained Voxelnet-based networks, a Region Proposal Network (RPN) and…
Recently, Spiking Neural Networks (SNNs), enjoying extreme energy efficiency, have drawn much research attention on 2D visual recognition and shown gradually increasing application potential. However, it still remains underexplored whether…
Point cloud analysis is an area of increasing interest due to the development of 3D sensors that are able to rapidly measure the depth of scenes accurately. Unfortunately, applying deep learning techniques to perform point cloud analysis is…
Scene flow is a powerful tool for capturing the motion field of 3D point clouds. However, it is difficult to directly apply flow-based models to dynamic point cloud classification since the unstructured points make it hard or even…
With the tide of artificial intelligence, we try to apply deep learning to understand 3D data. Point cloud is an important 3D data structure, which can accurately and directly reflect the real world. In this paper, we propose a simple and…
As a fundamental task for indoor scene understanding, 3D object detection has been extensively studied, and the accuracy on indoor point cloud data has been substantially improved. However, existing researches have been conducted on limited…