Related papers: Geometry-to-Image Synthesis-Driven Generative Poin…

3D LiDAR scanners are playing an increasingly important role in autonomous driving as they can generate depth information of the environment. However, creating large 3D LiDAR point cloud datasets with point-level labels requires a…

We introduce a novel 3D generative method, Generative 3D Reconstruction (G3DR) in ImageNet, capable of generating diverse and high-quality 3D objects from single images, addressing the limitations of existing methods. At the heart of our…

Three-dimensional (3D) fingerprints preserve global finger geometry and local ridge structure while avoiding contact-induced deformation, but they remain difficult to integrate with legacy two-dimensional (2D) fingerprint systems. This…

For a long time, the point cloud completion task has been regarded as a pure generation task. After obtaining the global shape code through the encoder, a complete point cloud is generated using the shape priorly learnt by the networks.…

Point cloud registration is an important task in robotics and autonomous driving to estimate the ego-motion of the vehicle. Recent advances following the coarse-to-fine manner show promising potential in point cloud registration. However,…

Probabilistic point cloud registration methods are becoming more popular because of their robustness. However, unlike point-to-plane variants of iterative closest point (ICP) which incorporate local surface geometric information such as…

Representation and generative learning, as reconstruction-based methods, have demonstrated their potential for mutual reinforcement across various domains. In the field of point cloud processing, although existing studies have adopted…

In this paper, we propose a graph neural network to detect objects from a LiDAR point cloud. Towards this end, we encode the point cloud efficiently in a fixed radius near-neighbors graph. We design a graph neural network, named Point-GNN,…

Point cloud segmentation is a fundamental task in 3D scene understanding. Its progress is constrained by the high cost and time required for dense 3D annotations, making labeled samples difficult to obtain. Beyond annotation scarcity,…

We present DeepICP - a novel end-to-end learning-based 3D point cloud registration framework that achieves comparable registration accuracy to prior state-of-the-art geometric methods. Different from other keypoint based methods where a…

We present PointFusion, a generic 3D object detection method that leverages both image and 3D point cloud information. Unlike existing methods that either use multi-stage pipelines or hold sensor and dataset-specific assumptions,…

In this paper, we propose a coarse-to-fine integration solution inspired by the classical ICP algorithm, to pairwise 3D point cloud registration with two improvements of hybrid metric spaces (eg, BSC feature and Euclidean geometry spaces)…

Point clouds are a very efficient way to represent volumetric data in medical imaging. First, they do not occupy resources for empty spaces and therefore can avoid trade-offs between resolution and field-of-view for voxel-based 3D…

Recent progress in 3D generation has been driven largely by models conditioned on images or text, while readily available 3D priors are still underused. In many real-world scenarios, the visible-region point cloud are easy to obtain from…

Multi-view point cloud registration is fundamental in 3D reconstruction. Since there are close connections between point clouds captured from different viewpoints, registration performance can be enhanced if these connections be harnessed…

In recent years, point cloud generation has gained significant attention in 3D generative modeling. Among existing approaches, point-based methods directly generate point clouds without relying on other representations such as latent…

Self-supervised learning of point cloud aims to leverage unlabeled 3D data to learn meaningful representations without reliance on manual annotations. However, current approaches face challenges such as limited data diversity and inadequate…

Existing networks directly learn feature representations on 3D point clouds for shape analysis. We argue that 3D point clouds are highly redundant and hold irregular (permutation-invariant) structure, which makes it difficult to achieve…

We introduce the Shape-Image Multimodal Network (SIM-Net), a novel 2D image classification architecture that integrates 3D point cloud representations inferred directly from RGB images. Our key contribution lies in a pixel-to-point…

Recent advances in deep learning have improved 3D point cloud registration but increased graphics processing unit (GPU) memory usage, often requiring preliminary sampling that reduces accuracy. We propose an overlapping region sampling…