The paper explores the optimization of sparse convolution for 3D point cloud analysis on Graphics Processing Units (GPUs) using CUDA technology. With the increasing use of LiDAR and 3D sensors,…
Continue readingThis research investigates how different observation spaces affect robot learning. The authors focus on three main modalities: RGB, RGB-D, and point cloud. Through extensive testing on various tasks, they found…
Continue readingODIN (Omni-Dimensional INstance segmentation) is a model proposed to challenge the belief that 2D and 3D perception require distinct model architectures. ODIN can segment and label both 2D RGB images…
Continue readingThe article introduces a novel coarse-to-fine approach for 3D instance segmentation, named Spherical Mask. It is based on spherical representation, which overcomes limitations of existing methods, such as instance size…
Continue readingThis academic paper introduces PillarNeSt, a new technique for 3D object detection in point clouds. The authors highlight the effectiveness of 2D backbone scaling and pretraining for pillar-based 3D object…
Continue readingThis research proposes a system for deformable object reconstruction and segmentation from a single point cloud. This method is beneficial for robot-assisted surgical applications, where the ability to identify and…
Continue readingThe article introduces Look at Robot Base Once (LRBO), a novel method for hand-eye calibration in robotic systems. This process is crucial in estimating the transformation matrix between a camera…
Continue readingThe paper introduces a new Cross-Modal Information-Guided Network (CMIGNet) for point cloud registration. Traditional methods rely solely on features from points, leading to limitations such as lack of texture information…
Continue readingThe article discusses UltraLiDAR, a system designed to address the issues of sparse point clouds captured by low-beam LiDAR. This data-driven framework is used for scene-level LiDAR completion, generation, and…
Continue readingThe article presents a new method called Point Regress AutoEncoder (Point-RAE) for regressive autoencoders in point cloud self-supervised learning. The method decouples functions between the decoder and encoder by introducing…
Continue readingLooks like you're using an ad blocker. Please support us by disabling these ad blocker.
