Related papers: Learning Geometry-Disentangled Representation for …
Semantic segmentation of point clouds, aiming to assign each point a semantic category, is critical to 3D scene understanding.Despite of significant advances in recent years, most of existing methods still suffer from either the…
We present a novel non-iterative learnable method for partial-to-partial 3D shape registration. The partial alignment task is extremely complex, as it jointly tries to match between points and identify which points do not appear in the…
Due to limitations in acquisition equipment, noise perturbations often corrupt 3-D point clouds, hindering down-stream tasks such as surface reconstruction, rendering, and further processing. Existing 3-D point cloud denoising methods…
Depth completion is a key task in autonomous driving, aiming to complete sparse LiDAR depth measurements into high-quality dense depth maps through image guidance. However, existing methods usually treat depth maps as an additional channel…
As the basic task of point cloud analysis, classification is fundamental but always challenging. To address some unsolved problems of existing methods, we propose a network that captures geometric features of point clouds for better…
Point cloud completion is essential for robotic perception, object reconstruction and supporting downstream tasks like grasp planning, obstacle avoidance, and manipulation. However, incomplete geometry caused by self-occlusion and sensor…
Point clouds, being the simple and compact representation of surface geometry of 3D objects, have gained increasing popularity with the evolution of deep learning networks for classification and segmentation tasks. Unlike human, teaching…
Exploring contextual information in the local region is important for shape understanding and analysis. Existing studies often employ hand-crafted or explicit ways to encode contextual information of local regions. However, it is hard to…
In recent years, point clouds have become increasingly popular for representing three-dimensional (3D) visual objects and scenes. To efficiently store and transmit point clouds, compression methods have been developed, but they often result…
Geometry and topology constitute complementary descriptors of three-dimensional shape, yet existing benchmark datasets primarily capture geometric information while neglecting topological structure. This work addresses this limitation by…
Point cloud, an efficient 3D object representation, has become popular with the development of depth sensing and 3D laser scanning techniques. It has attracted attention in various applications such as 3D tele-presence, navigation for…
This work considers a new task in geometric deep learning: generating a triangulation among a set of points in 3D space. We present PointTriNet, a differentiable and scalable approach enabling point set triangulation as a layer in 3D…
Environmental perception systems are crucial for high-precision mapping and autonomous navigation, with LiDAR serving as a core sensor providing accurate 3D point cloud data. Efficiently processing unstructured point clouds while extracting…
3D point cloud interpretation is a challenging task due to the randomness and sparsity of the component points. Many of the recently proposed methods like PointNet and PointCNN have been focusing on learning shape descriptions from point…
Segmentation of three-dimensional (3D) point clouds is an important task for autonomous systems. However, success of segmentation algorithms depends greatly on the quality of the underlying point clouds (resolution, completeness etc.). In…
In this paper, we propose Attention Based Decomposition Network (ABD-Net), for point cloud decomposition into basic geometric shapes namely, plane, sphere, cone and cylinder. We show improved performance of 3D object classification using…
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…
Measuring and alleviating the discrepancies between the synthetic (source) and real scene (target) data is the core issue for domain adaptive semantic segmentation. Though recent works have introduced depth information in the source domain…
Point cloud semantic segmentation from projected views, such as range-view (RV) and bird's-eye-view (BEV), has been intensively investigated. Different views capture different information of point clouds and thus are complementary to each…
3D object detection often involves complicated training and testing pipelines, which require substantial domain knowledge about individual datasets. Inspired by recent non-maximum suppression-free 2D object detection models, we propose a 3D…