Results 21 to 30 of about 6,440,801 (359)
PointRCNN: 3D Object Proposal Generation and Detection From Point Cloud [PDF]
Computer Vision and Pattern Recognition, 2018 In this paper, we propose PointRCNN for 3D object detection from raw point cloud. The whole framework is composed of two stages: stage-1 for the bottom-up 3D proposal generation and stage-2 for refining proposals in the canonical coordinates to obtain ...
Shaoshuai Shi +2 more
semanticscholar +1 more source
PC2: Projection-Conditioned Point Cloud Diffusion for Single-Image 3D Reconstruction [PDF]
Computer Vision and Pattern Recognition, 2023 Reconstructing the 3D shape of an object from a single RGB image is a long-standing problem in computer vision. In this paper, we propose a novel method for single-image 3D reconstruction which generates a sparse point cloud via a conditional denoising ...
Luke Melas-Kyriazi +2 more
semanticscholar +1 more source
A method of point cloud data block registration with considering distance from point to surface [PDF]
Bulletin of the Polish Academy of Sciences: Technical Sciences, 2022 The number of scanner stations used to acquire point cloud data is limited, resulting in poor data registration. As a result, a cloud point block registration approach was proposed that took into account the distance between the point and the surface ...
Yinju Lu, Mingyi Duan, Shuguang Dai
doaj +1 more source
Segment Any Point Cloud Sequences by Distilling Vision Foundation Models [PDF]
Neural Information Processing Systems, 2023 Recent advancements in vision foundation models (VFMs) have opened up new possibilities for versatile and efficient visual perception. In this work, we introduce Seal, a novel framework that harnesses VFMs for segmenting diverse automotive point cloud ...
You-Chen Liu +7 more
semanticscholar +1 more source
Geodesics on Point Clouds [PDF]
Mathematical Problems in Engineering, 2014 We present a novel framework to compute geodesics on implicit surfaces and point clouds. Our framework consists of three parts, particle based approximate geodesics on implicit surfaces, Cartesian grid based approximate geodesics on point clouds, and geodesic correction.
Hongchuan Yu, Jian J. Zhang, Zheng Jiao
openaire +2 more sources
Sensors, 2022 As one of the best means of obtaining the geometry information of special shaped structures, point cloud data acquisition can be achieved by laser scanning or photogrammetry.
Xinming Pu +3 more
doaj +1 more source
Rotation-Invariant Transformer for Point Cloud Matching [PDF]
Computer Vision and Pattern Recognition, 2023 The intrinsic rotation invariance lies at the core of matching point clouds with handcrafted descriptors. However, it is widely despised by recent deep matchers that obtain the rotation invariance extrinsically via data augmentation. As the finite number
Hao Yu +6 more
semanticscholar +1 more source
Picking Towels in Point Clouds [PDF]
Sensors, 2019 Picking clothing has always been a great challenge in laundry or textile industry automation, especially when some clothes are of the same colors, material and entangled with each other. In order to solve the problem, we present a grasp pose determination method to pick towels placed in a laundry basket or on a table. In our method, it is not needed to
Wang, Xiaoman +5 more
openaire +3 more sources
Topological Point Cloud Clustering
Proceedings of the 40th International Conference on Machine Learning. International Conference on Machine Learning, ICML 2023, Honolulu, USA, 2023 Accepted at the 40th International Conference on Machine Learning (ICML), 2023.
Grande, Vincent P., Schaub, Michael T.
openaire +3 more sources
FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer [PDF]
Computer Vision and Pattern Recognition, 2023 Transformer, as an alternative to CNN, has been proven effective in many modalities (e.g., texts and images). For 3D point cloud transformers, existing efforts focus primarily on pushing their accuracy to the state-of-the-art level.
Zhijian Liu +4 more
semanticscholar +1 more source