IEEE

PatchMixing Masked Autoencoders for 3D Point Cloud Self-Supervised Learning

Abstract: Recently, Point-MAE has extended Masked Autoencoders (MAE) to point clouds for 3D self-supervised learning, which however faces two problems: (1) the shape similarity between the masked ...
IEEE

Prototype-Voxel Contrastive Learning for LiDAR Point Cloud Panoptic Segmentation

Abstract: LiDAR point cloud panoptic segmentation, including both semantic and instance segmentation, plays a critical role in meticulous scene understanding for autonomous driving. Existing 3D ...
IEEE

Neural Informed RRT*: Learning-based Path Planning with Point Cloud State Representations under Admissible Ellipsoidal Constraints

Abstract: Sampling-based planning algorithms like Rapidly-exploring Random Tree (RRT) are versatile in solving path planning problems. RRT* offers asymptotic optimality but requires growing the tree ...
IEEE

Deep Learning-Based Point Cloud Compression: An In-Depth Survey and Benchmark

Abstract: With the maturity of 3D capture technology, the explosive growth of point cloud data has burdened the storage and transmission process. Traditional hybrid point cloud compression (PCC) tools ...
IEEE

DeepPSF: On-Orbit Point Spread Function Estimation of Space Camera With Deep Learning

Abstract: Obtaining an on-orbit space camera’s point spread function (PSF) is challenging but necessary for remote sensing image (RSI) restoration. Current methods rely on regular ground targets, ...
IEEE

A Survey of Label-Efficient Deep Learning for 3D Point Clouds

Abstract: In the past decade, deep neural networks have achieved significant progress in point cloud learning. However, collecting large-scale precisely-annotated point clouds is extremely laborious ...
IEEE

Unsupervised Point Cloud Registration by Learning Unified Gaussian Mixture Models

Abstract: Sampling noise and density variation widely exist in the point cloud acquisition process, leading to few accurate point-to-point correspondences. Since they rely on point-to-point ...
IEEE

Dual Branch Graph Representation Learning-Based Approach for Next Point-of-Interest Recommendation

Abstract: Next Point-of-Interest (POI) recommendation, a sub-task of POI recommendation, focuses on predicting the next POI a user will visit, relying on the user’s sequential check-in history. In ...
IEEE

Unsupervised 3D Point Cloud Completion via Multi-View Adversarial Learning

Abstract: In real-world scenarios, scanned point clouds are often incomplete due to occlusion issues. The tasks of self-supervised and weakly-supervised point cloud completion involve reconstructing ...
IEEE

A Content-Adaptive Hierarchical Deep Learning Model for Detecting Arbitrary-Oriented Road Surface Elements Using MLS Point Clouds

Abstract: Accurate and automatic detection of road surface element (such as road marking or manhole cover) information is the basis and key to many applications. To efficiently obtain the information ...
football

Chelsea learn Nottingham Forest's sack decision on Ange Postecoglou ahead of Blues clash

Despite a rocky start, Nottingham Forest are reportedly leaning towards retaining Ange Postecoglou at the City Ground for the time being. The former Tottenham boss has found himself under immediate ...
IEEE

Linked Dynamic Graph CNN: Learning through Point Cloud by Linking Hierarchical Features

Abstract: Learning through a point cloud is attractive be-cause a point cloud contains geometric data and can help robots understand environments in a robust manner. However, a point cloud is sparse, ...