Related papers: SPLATNet: Sparse Lattice Networks for Point Cloud …

Deep neural networks require specific layers to process point clouds, as the scattered and irregular location of 3D points prevents the use of conventional convolutional filters. We introduce the composite layer, a flexible and general…

We propose a new approach for 3D instance segmentation based on sparse convolution and point affinity prediction, which indicates the likelihood of two points belonging to the same instance. The proposed network, built upon submanifold…

Convolutional Neural Networks (CNNs) have performed extremely well on data represented by regularly arranged grids such as images. However, directly leveraging the classic convolution kernels or parameter sharing mechanisms on sparse 3D…

The analysis of 3D point clouds has diverse applications in robotics, vision and graphics. Processing them presents specific challenges since they are naturally sparse, can vary in spatial resolution and are typically unordered. Graph-based…

Point clouds data, as one kind of representation of 3D objects, are the most primitive output obtained by 3D sensors. Unlike 2D images, point clouds are disordered and unstructured. Hence it is not straightforward to apply classification…

Deep learning systems extensively use convolution operations to process input data. Though convolution is clearly defined for structured data such as 2D images or 3D volumes, this is not true for other data types such as sparse point…

This work introduces a new training and compression pipeline to build Nested Sparse ConvNets, a class of dynamic Convolutional Neural Networks (ConvNets) suited for inference tasks deployed on resource-constrained devices at the edge of the…

Processing large point clouds is a challenging task. Therefore, the data is often downsampled to a smaller size such that it can be stored, transmitted and processed more efficiently without incurring significant performance degradation.…

This paper presents a convolutional layer that is able to process sparse input features. As an example, for image recognition problems this allows an efficient filtering of signals that do not lie on a dense grid (like pixel position), but…

Selection is a fundamental task in exploratory analysis and visualization of 3D point clouds. Prior researches on selection methods were developed mainly based on heuristics such as local point density, thus limiting their applicability in…

Semantic segmentation of point clouds in autonomous driving datasets requires techniques that can process large numbers of points efficiently. Sparse 3D convolutions have become the de-facto tools to construct deep neural networks for this…

3D neural networks have become prevalent for many 3D vision tasks including object detection, segmentation, registration, and various perception tasks for 3D inputs. However, due to the sparsity and irregularity of 3D data, custom 3D…

Processing large point clouds is a challenging task. Therefore, the data is often sampled to a size that can be processed more easily. The question is how to sample the data? A popular sampling technique is Farthest Point Sampling (FPS).…

We propose a novel, end-to-end trainable, deep network called ParSeNet that decomposes a 3D point cloud into parametric surface patches, including B-spline patches as well as basic geometric primitives. ParSeNet is trained on a large-scale…

Learning on point cloud is eagerly in demand because the point cloud is a common type of geometric data and can aid robots to understand environments robustly. However, the point cloud is sparse, unstructured, and unordered, which cannot be…

Point cloud is one of the widely used techniques for representing and storing 3D geometric data. In the past several methods have been proposed for processing point clouds. Methods such as PointNet and FoldingNet have shown promising…

Point clouds are characterized by irregularity and unstructuredness, which pose challenges in efficient data exploitation and discriminative feature extraction. In this paper, we present an unsupervised deep neural architecture called…

Modeling object dynamics with a neural network is an important problem with numerous applications. Most recent work has been based on graph neural networks. However, physics happens in 3D space, where geometric information potentially plays…

We have implemented a convolutional neural network designed for processing sparse three-dimensional input data. The world we live in is three dimensional so there are a large number of potential applications including 3D object recognition…

We propose an approach to instance segmentation from 3D point clouds based on dynamic convolution. This enables it to adapt, at inference, to varying feature and object scales. Doing so avoids some pitfalls of bottom up approaches,…