Related papers: RISurConv: Rotation Invariant Surface Attention-Au…

Recently Transformer-based models have advanced point cloud understanding by leveraging self-attention mechanisms, however, these methods often overlook latent information in less prominent regions, leading to increased sensitivity to…

3D point cloud segmentation is an important function that helps robots understand the layout of their surrounding environment and perform tasks such as grasping objects, avoiding obstacles, and finding landmarks. Current segmentation…

Point cloud processing is a challenging task due to its sparsity and irregularity. Prior works introduce delicate designs on either local feature aggregator or global geometric architecture, but few combine both advantages. We propose…

3D instance segmentation aims to predict a set of object instances in a scene, representing them as binary foreground masks with corresponding semantic labels. Currently, transformer-based methods are gaining increasing attention due to…

The paper presents a learning-based method for computing a discriminative 3D point cloud descriptor for place recognition purposes. Existing methods, such as PointNetVLAD, are based on unordered point cloud representation. They use PointNet…

Deep neural networks are widely used for understanding 3D point clouds. At each point convolution layer, features are computed from local neighborhoods of 3D points and combined for subsequent processing in order to extract semantic…

We present PPF-FoldNet for unsupervised learning of 3D local descriptors on pure point cloud geometry. Based on the folding-based auto-encoding of well known point pair features, PPF-FoldNet offers many desirable properties: it necessitates…

Existing 3D instance segmentation methods are predominated by the bottom-up design -- manually fine-tuned algorithm to group points into clusters followed by a refinement network. However, by relying on the quality of the clusters, these…

Existing point-cloud based 3D object detectors use convolution-like operators to process information in a local neighbourhood with fixed-weight kernels and aggregate global context hierarchically. However, non-local neural networks and…

Point cloud classification plays an important role in a wide range of airborne light detection and ranging (LiDAR) applications, such as topographic mapping, forest monitoring, power line detection, and road detection. However, due to the…

Existing convolutional learning methods for 3D point cloud data are divided into two paradigms: point-based methods that preserve geometric precision but often face performance challenges, and voxel-based methods that achieve high…

Incomplete point clouds captured by 3D sensors often result in the loss of both geometric and semantic information. Most existing point cloud completion methods are built on rotation-variant frameworks trained with data in canonical poses,…

Point cloud analysis is very challenging, as the shape implied in irregular points is difficult to capture. In this paper, we propose RS-CNN, namely, Relation-Shape Convolutional Neural Network, which extends regular grid CNN to irregular…

In this paper, we propose PASS3D to achieve point-wise semantic segmentation for 3D point cloud. Our framework combines the efficiency of traditional geometric methods with robustness of deep learning methods, consisting of two stages: At…

A symmetry on rigid motion is one of the salient factors in efficient learning of 3D point cloud problems. Group convolution has been a representative method to extract equivariant features, but its realizations have struggled to retain…

We introduce FPConv, a novel surface-style convolution operator designed for 3D point cloud analysis. Unlike previous methods, FPConv doesn't require transforming to intermediate representation like 3D grid or graph and directly works on…

Real-world point clouds usually suffer from incompleteness and display different poses. While current point cloud completion methods excel in reproducing complete point clouds with consistent poses as seen in the training set, their…

Point-cloud is an efficient way to represent 3D world. Analysis of point-cloud deals with understanding the underlying 3D geometric structure. But due to the lack of smooth topology, and hence the lack of neighborhood structure, standard…

In this paper, we introduce a novel approach that harnesses both 2D and 3D attentions to enable highly accurate depth completion without requiring iterative spatial propagations. Specifically, we first enhance a baseline convolutional depth…

Many recent works show that a spatial manipulation module could boost the performances of deep neural networks (DNNs) for 3D point cloud analysis. In this paper, we aim to provide an insight into spatial manipulation modules. Firstly, we…