Related papers: VoxelNet: End-to-End Learning for Point Cloud Base…
Recent advances in 3D sensing have created unique challenges for computer vision. One fundamental challenge is finding a good representation for 3D sensor data. Most popular representations (such as PointNet) are proposed in the context of…
Semantic scene understanding from point clouds is particularly challenging as the points reflect only a sparse set of the underlying 3D geometry. Previous works often convert point cloud into regular grids (e.g. voxels or bird-eye view…
The performance of point cloud 3D object detection hinges on effectively representing raw points, grid-based voxels or pillars. Recent two-stage 3D detectors typically take the point-voxel-based R-CNN paradigm, i.e., the first stage resorts…
Large-scale point cloud generated from 3D sensors is more accurate than its image-based counterpart. However, it is seldom used in visual pose estimation due to the difficulty in obtaining 2D-3D image to point cloud correspondences. In this…
We present Point-Voxel CNN (PVCNN) for efficient, fast 3D deep learning. Previous work processes 3D data using either voxel-based or point-based NN models. However, both approaches are computationally inefficient. The computation cost and…
Point cloud based retrieval for place recognition is still a challenging problem due to drastic appearance and illumination changes of scenes in changing environments. Existing deep learning based global descriptors for the retrieval task…
The performance of 3D object detection models over point clouds highly depends on their capability of modeling local geometric patterns. Conventional point-based models exploit local patterns through a symmetric function (e.g. max pooling)…
Effective point cloud processing is crucial to LiDARbased autonomous driving systems. The capability to understand features at multiple scales is required for object detection of intelligent vehicles, where road users may appear in…
Object detection from 3D point clouds remains a challenging task, though recent studies pushed the envelope with the deep learning techniques. Owing to the severe spatial occlusion and inherent variance of point density with the distance to…
Recent Transformer-based 3D object detectors learn point cloud features either from point- or voxel-based representations. However, the former requires time-consuming sampling while the latter introduces quantization errors. In this paper,…
Robot localization using a built map is essential for a variety of tasks including accurate navigation and mobile manipulation. A popular approach to robot localization is based on image-to-point cloud registration, which combines…
Lidar based 3D object detection and classification tasks are essential for autonomous driving(AD). A lidar sensor can provide the 3D point cloud data reconstruction of the surrounding environment. However, real time detection in 3D point…
In this paper, we present new feature encoding methods for Detection of 3D objects in point clouds. We used a graph neural network (GNN) for Detection of 3D objects namely cars, pedestrians, and cyclists. Feature encoding is one of the…
Efficiently and accurately detecting people from 3D point cloud data is of great importance in many robotic and autonomous driving applications. This fundamental perception task is still very challenging due to (i) significant deformations…
Many applications in robotics and human-computer interaction can benefit from understanding 3D motion of points in a dynamic environment, widely noted as scene flow. While most previous methods focus on stereo and RGB-D images as input, few…
The recent advancements in point cloud learning have enabled intelligent vehicles and robots to comprehend 3D environments better. However, processing large-scale 3D scenes remains a challenging problem, such that efficient downsampling…
Recent years have witnessed huge successes in 3D object detection to recognize common objects for autonomous driving (e.g., vehicles and pedestrians). However, most methods rely heavily on a large amount of well-labeled training data. This…
The existing 3D deep learning methods adopt either individual point-based features or local-neighboring voxel-based features, and demonstrate great potential for processing 3D data. However, the point based models are inefficient due to the…
We propose a novel, conceptually simple and general framework for instance segmentation on 3D point clouds. Our method, called 3D-BoNet, follows the simple design philosophy of per-point multilayer perceptrons (MLPs). The framework directly…
In this paper, we propose a monocular 3D object detection framework in the domain of autonomous driving. Unlike previous image-based methods which focus on RGB feature extracted from 2D images, our method solves this problem in the…