English
Related papers

Related papers: Learning to Sample

200 papers

Scene understanding based on LiDAR point cloud is an essential task for autonomous cars to drive safely, which often employs spherical projection to map 3D point cloud into multi-channel 2D images for semantic segmentation. Most existing…

Computer Vision and Pattern Recognition · Computer Science 2021-07-19 Aoran Xiao , Xiaofei Yang , Shijian Lu , Dayan Guan , Jiaxing Huang

In recent years, network embedding methods have garnered increasing attention because of their effectiveness in various information retrieval tasks. The goal is to learn low-dimensional representations of vertexes in an information network…

Social and Information Networks · Computer Science 2017-11-02 Chih-Ming Chen , Yi-Hsuan Yang , Yian Chen , Ming-Feng Tsai

Deep neural networks are widely used for understanding 3D point clouds. At each point convolution layer, features are computed from local neighborhoods of 3D points and combined for subsequent processing in order to extract semantic…

Computer Vision and Pattern Recognition · Computer Science 2021-05-13 Jiayun Wang , Rudrasis Chakraborty , Stella X. Yu

Deep convolutional neural networks (CNNs) have shown outstanding performance in the task of semantically segmenting images. Applying the same methods on 3D data still poses challenges due to the heavy memory requirements and the lack of…

Computer Vision and Pattern Recognition · Computer Science 2021-08-21 Radu Alexandru Rosu , Peer Schütt , Jan Quenzel , Sven Behnke

Much effort has been put into developing samplers with specific properties, such as producing blue noise, low-discrepancy, lattice or Poisson disk samples. These samplers can be slow if they rely on optimization processes, may rely on a…

We propose a new supervized learning framework for oversegmenting 3D point clouds into superpoints. We cast this problem as learning deep embeddings of the local geometry and radiometry of 3D points, such that the border of objects presents…

Computer Vision and Pattern Recognition · Computer Science 2019-04-04 Loic Landrieu , Mohamed Boussaha

Many existing approaches for 3D point cloud semantic segmentation are fully supervised. These fully supervised approaches heavily rely on large amounts of labeled training data that are difficult to obtain and cannot segment new classes…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Na Zhao , Tat-Seng Chua , Gim Hee Lee

In this case study, we present a data-efficient point cloud segmentation pipeline and training framework for robust segmentation of unimproved roads and seven other classes. Our method employs a two-stage training framework: first, a…

Image and Video Processing · Electrical Eng. & Systems 2025-08-29 Andrew Yarovoi , Christopher R. Valenta

Recent deepfake detection studies often treat unseen sample detection as a ``zero-shot" task, training on images generated by known models but generalizing to unknown ones. A key real-world challenge arises when a model performs poorly on…

Computer Vision and Pattern Recognition · Computer Science 2025-08-14 Shibo Yao , Renshuai Tao , Xiaolong Zheng , Chao Liang , Chunjie Zhang

Fast and efficient semantic segmentation of large-scale LiDAR point clouds is a fundamental problem in autonomous driving. To achieve this goal, the existing point-based methods mainly choose to adopt Random Sampling strategy to process…

Computer Vision and Pattern Recognition · Computer Science 2024-03-07 XianFeng Han , Huixian Cheng , Hang Jiang , Dehong He , Guoqiang Xiao

3D perception in point clouds is transforming the perception ability of future intelligent machines. Point cloud algorithms, however, are plagued by irregular memory accesses, leading to massive inefficiencies in the memory sub-system,…

Hardware Architecture · Computer Science 2022-04-25 Yu Feng , Gunnar Hammonds , Yiming Gan , Yuhao Zhu

Point clouds are often sparse and incomplete. Existing shape completion methods are incapable of generating details of objects or learning the complex point distributions. To this end, we propose a cascaded refinement network together with…

Computer Vision and Pattern Recognition · Computer Science 2020-06-08 Xiaogang Wang , Marcelo H Ang , Gim Hee Lee

3D point cloud segmentation is an important function that helps robots understand the layout of their surrounding environment and perform tasks such as grasping objects, avoiding obstacles, and finding landmarks. Current segmentation…

Computer Vision and Pattern Recognition · Computer Science 2021-03-17 Jingdao Chen , Zsolt Kira , Yong K. Cho

Estimating the normal of a point requires constructing a local patch to provide center-surrounding context, but determining the appropriate neighborhood size is difficult when dealing with different data or geometries. Existing methods…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Qing Li , Huifang Feng , Kanle Shi , Yue Gao , Yi Fang , Yu-Shen Liu , Zhizhong Han

We propose a novel normal estimation method called HSurf-Net, which can accurately predict normals from point clouds with noise and density variations. Previous methods focus on learning point weights to fit neighborhoods into a geometric…

Computer Vision and Pattern Recognition · Computer Science 2022-10-14 Qing Li , Yu-Shen Liu , Jin-San Cheng , Cheng Wang , Yi Fang , Zhizhong Han

Among 2D convolutional networks on point clouds, point-based approaches consume point clouds of fixed size directly. By analysis of PointNet, a pioneer in introducing deep learning into point sets, we reveal that current point-based methods…

Computer Vision and Pattern Recognition · Computer Science 2021-08-11 Zhenpeng Chen , Yuan li

Recently, great progress has been made in 3D deep learning with the emergence of deep neural networks specifically designed for 3D point clouds. These networks are often trained from scratch or from pre-trained models learned purely from…

Computer Vision and Pattern Recognition · Computer Science 2022-10-31 Bach Tran , Binh-Son Hua , Anh Tuan Tran , Minh Hoai

Point clouds are an increasingly ubiquitous input modality and the raw signal can be efficiently processed with recent progress in deep learning. This signal may, often inadvertently, capture sensitive information that can leak semantic and…

Computer Vision and Pattern Recognition · Computer Science 2022-03-24 Ayush Chopra , Abhinav Java , Abhishek Singh , Vivek Sharma , Ramesh Raskar

Learning and selecting important points on a point cloud is crucial for point cloud understanding in various applications. Most of early methods selected the important points on 3D shapes by analyzing the intrinsic geometric properties of…

Computer Vision and Pattern Recognition · Computer Science 2023-05-11 Xinhai Liu , Zhizhong Han , Sanghuk Lee , Yan-Pei Cao , Yu-Shen Liu

Reconstructing a 3D shape based on a single sketch image is challenging due to the large domain gap between a sparse, irregular sketch and a regular, dense 3D shape. Existing works try to employ the global feature extracted from sketch to…

Computer Vision and Pattern Recognition · Computer Science 2022-12-27 Chenjian Gao , Qian Yu , Lu Sheng , Yi-Zhe Song , Dong Xu