English
Related papers

Related papers: What Can be Seen is What You Get: Structure Aware …

200 papers

For 3D object detection, labeling lidar point cloud is difficult, so data augmentation is an important module to make full use of precious annotated data. As a widely used data augmentation method, GT-sample effectively improves detection…

Computer Vision and Pattern Recognition · Computer Science 2022-11-22 Xuzhong Hu , Zaipeng Duan , Jie Ma

We present an improved version of PointRCNN for 3D object detection, in which a multi-branch backbone network is adopted to handle the non-uniform density of point clouds. An uncertainty-based sampling policy is proposed to deal with the…

Computer Vision and Pattern Recognition · Computer Science 2021-01-11 Jie Li , Yu Hu

Despite the extensive usage of point clouds in 3D vision, relatively limited data are available for training deep neural networks. Although data augmentation is a standard approach to compensate for the scarcity of data, it has been less…

Computer Vision and Pattern Recognition · Computer Science 2021-10-12 Sihyeon Kim , Sanghyeok Lee , Dasol Hwang , Jaewon Lee , Seong Jae Hwang , Hyunwoo J. Kim

A considerable amount of research is concerned with the generation of realistic sensor data. LiDAR point clouds are generated by complex simulations or learned generative models. The generated data is usually exploited to enable or improve…

Computer Vision and Pattern Recognition · Computer Science 2022-09-01 Larissa T. Triess , Christoph B. Rist , David Peter , J. Marius Zöllner

Data augmentation is widely used to train deep learning models to address data scarcity. However, traditional data augmentation (TDA) typically relies on simple geometric transformation, such as random rotation and rescaling, resulting in…

Computer Vision and Pattern Recognition · Computer Science 2025-08-27 Dekai Zhu , Stefan Gavranovic , Flavien Boussuge , Benjamin Busam , Slobodan Ilic

Point clouds arising from structured data, mainly as a result of CT scans, provides special properties on the distribution of points and the distances between those. Yet often, the amount of data provided can not compare to unstructured…

Computational Geometry · Computer Science 2017-02-16 Franziska Lippoldt , Hartmut Schwandt

LiDAR point clouds are widely used in autonomous driving and consist of large numbers of 3D points captured at high frequency to represent surrounding objects such as vehicles, pedestrians, and traffic signs. While this dense data enables…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Z. Rozsa , Á. Madaras , Q. Wei , X. Lu , M. Golarits , H. Yuan , T. Sziranyi , R. Hamzaoui

Semantic segmentation and semantic edge detection can be seen as two dual problems with close relationships in computer vision. Despite the fast evolution of learning-based 3D semantic segmentation methods, little attention has been drawn…

Computer Vision and Pattern Recognition · Computer Science 2021-07-30 Zeyu Hu , Mingmin Zhen , Xuyang Bai , Hongbo Fu , Chiew-lan Tai

In this paper, we introduce a reinforcement learning approach utilizing a novel topology-based information gain metric for directing the next best view of a noisy 3D sensor. The metric combines the disjoint sections of an observed surface…

Robotics · Computer Science 2021-03-23 Christopher Collander , William J. Beksi , Manfred Huber

It is counter-intuitive that multi-modality methods based on point cloud and images perform only marginally better or sometimes worse than approaches that solely use point cloud. This paper investigates the reason behind this phenomenon.…

Computer Vision and Pattern Recognition · Computer Science 2021-04-22 Wenwei Zhang , Zhe Wang , Chen Change Loy

The purpose of this work is to review the state-of-the-art LiDAR-based 3D object detection methods, datasets, and challenges. We describe novel data augmentation methods, sampling strategies, activation functions, attention mechanisms, and…

Computer Vision and Pattern Recognition · Computer Science 2022-04-04 Walter Zimmer , Emec Ercelik , Xingcheng Zhou , Xavier Jair Diaz Ortiz , Alois Knoll

Deep neural networks have established themselves as the state-of-the-art methodology in almost all computer vision tasks to date. But their application to processing data lying on non-Euclidean domains is still a very active area of…

Computer Vision and Pattern Recognition · Computer Science 2019-05-21 Chaitanya Kaul , Nick Pears , Suresh Manandhar

Semantic change detection is an important task in geoscience and earth observation. By producing a semantic change map for each temporal phase, both the land use land cover categories and change information can be interpreted. Recently some…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Chenyao Zhou , Haotian Zhang , Han Guo , Zhengxia Zou , Zhenwei Shi

Deep learning has achieved remarkable results in many computer vision tasks. Deep neural networks typically rely on large amounts of training data to avoid overfitting. However, labeled data for real-world applications may be limited. By…

Computer Vision and Pattern Recognition · Computer Science 2023-11-07 Suorong Yang , Weikang Xiao , Mengchen Zhang , Suhan Guo , Jian Zhao , Furao Shen

Despite data augmentation being a de facto technique for boosting the performance of deep neural networks, little attention has been paid to developing augmentation strategies for generative adversarial networks (GANs). To this end, we…

Computer Vision and Pattern Recognition · Computer Science 2021-02-02 Prateek Katiyar , Anna Khoreva

Three dimensional (3D) object recognition is becoming a key desired capability for many computer vision systems such as autonomous vehicles, service robots and surveillance drones to operate more effectively in unstructured environments.…

Computer Vision and Pattern Recognition · Computer Science 2021-08-25 Chenxi Xiao , Juan Wachs

Accurate 3D geometry acquisition is essential for a wide range of applications, such as computer graphics, autonomous driving, robotics, and augmented reality. However, raw point clouds acquired in real-world environments are often…

Graphics · Computer Science 2025-08-26 Jinxi Wang , Ben Fei , Dasith de Silva Edirimuni , Zheng Liu , Ying He , Xuequan Lu

Data augmentation is a technique to improve the generalization ability of machine learning methods by increasing the size of the dataset. However, since every augmentation method is not equally effective for every dataset, you need to…

Machine Learning · Computer Science 2022-05-31 Daisuke Oba , Shinnosuke Matsuo , Brian Kenji Iwana

3D LiDAR scanners are playing an increasingly important role in autonomous driving as they can generate depth information of the environment. However, creating large 3D LiDAR point cloud datasets with point-level labels requires a…

Computer Vision and Pattern Recognition · Computer Science 2018-04-03 Xiangyu Yue , Bichen Wu , Sanjit A. Seshia , Kurt Keutzer , Alberto L. Sangiovanni-Vincentelli

Change detection, i.e. identification per pixel of changes for some classes of interest from a set of bi-temporal co-registered images, is a fundamental task in the field of remote sensing. It remains challenging due to unrelated forms of…

Computer Vision and Pattern Recognition · Computer Science 2021-09-20 Foivos I. Diakogiannis , François Waldner , Peter Caccetta