Related papers: PointSSC: A Cooperative Vehicle-Infrastructure Poi…

Point cloud completion addresses filling in the missing parts of a partial point cloud obtained from depth sensors and generating a complete point cloud. Although there has been steep progress in the supervised methods on the synthetic…

Panoptic segmentation of point clouds is a crucial task that enables autonomous vehicles to comprehend their vicinity using their highly accurate and reliable LiDAR sensors. Existing top-down approaches tackle this problem by either…

Understanding the complex urban infrastructure with centimeter-level accuracy is essential for many applications from autonomous driving to mapping, infrastructure monitoring, and urban management. Aerial images provide valuable information…

3D point cloud semantic segmentation aims to group all points into different semantic categories, which benefits important applications such as point cloud scene reconstruction and understanding. Existing supervised point cloud semantic…

We propose ESSC-RM, a plug-and-play Enhancing framework for Semantic Scene Completion with a Refinement Module, which can be seamlessly integrated into existing SSC models. ESSC-RM operates in two phases: a baseline SSC network first…

We introduce ScanComplete, a novel data-driven approach for taking an incomplete 3D scan of a scene as input and predicting a complete 3D model along with per-voxel semantic labels. The key contribution of our method is its ability to…

Point cloud completion aims to recover partial geometric and topological shapes caused by equipment defects or limited viewpoints. Current methods either solely rely on the 3D coordinates of the point cloud to complete it or incorporate…

This paper revisits few-shot 3D point cloud semantic segmentation (FS-PCS), with a focus on two significant issues in the state-of-the-art: foreground leakage and sparse point distribution. The former arises from non-uniform point sampling,…

This study analyzes semantic segmentation performance across heterogeneously labeled point-cloud datasets relevant to public safety applications, including pre-incident planning systems derived from lidar scans. Using NIST's Point Cloud…

Geometrical structures and the internal local region relationship, such as symmetry, regular array, junction, etc., are essential for understanding a 3D shape. This paper proposes a point cloud feature extraction network named PointSCNet,…

While deep learning-based methods have demonstrated outstanding results in numerous domains, some important functionalities are missing. Resolution scalability is one of them. In this work, we introduce a novel architecture, dubbed…

Besides local features, global information plays an essential role in semantic segmentation, while recent works usually fail to explicitly extract the meaningful global information and make full use of it. In this paper, we propose a…

Place recognition is a challenging task in computer vision, crucial for enabling autonomous vehicles and robots to navigate previously visited environments. While significant progress has been made in learnable multimodal methods that…

Semantic shape completion is a challenging problem in 3D computer vision where the task is to generate a complete 3D shape using a partial 3D shape as input. We propose a learning-based approach to complete incomplete 3D shapes through…

Object classification using LiDAR 3D point cloud data is critical for modern applications such as autonomous driving. However, labeling point cloud data is labor-intensive as it requires human annotators to visualize and inspect the 3D data…

Semantic segmentation serves as a cornerstone of scene understanding in autonomous driving but continues to face significant challenges under complex conditions such as occlusion. Light field and LiDAR modalities provide complementary…

3D semantic occupancy prediction is an essential part of autonomous driving, focusing on capturing the geometric details of scenes. Off-road environments are rich in geometric information, therefore it is suitable for 3D semantic occupancy…

In this paper, a method for dense semantic 3D scene reconstruction from an RGB-D sequence is proposed to solve high-level scene understanding tasks. First, each RGB-D pair is consistently segmented into 2D semantic maps based on a camera…

Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal annotated support samples. While existing FS-PCS methods have shown promise, they primarily focus on unimodal point cloud…

We present a deep reinforcement learning method of progressive view inpainting for colored semantic point cloud scene completion under volume guidance, achieving high-quality scene reconstruction from only a single RGB-D image with severe…