中文
相关论文

相关论文: Class-Aware PillarMix: Can Mixed Sample Data Augme…

200 篇论文

We present PointAugment, a new auto-augmentation framework that automatically optimizes and augments point cloud samples to enrich the data diversity when we train a classification network. Different from existing auto-augmentation methods…

计算机视觉与模式识别 · 计算机科学 2020-03-23 Ruihui Li , Xianzhi Li , Pheng-Ann Heng , Chi-Wing Fu

Data augmentation techniques, such as simple image transformations and combinations, are highly effective at improving the generalization of computer vision models, especially when training data is limited. However, such techniques are…

机器学习 · 计算机科学 2023-11-03 Wenxuan Bao , Francesco Pittaluga , Vijay Kumar B G , Vincent Bindschaedler

3D object detection plays a fundamental role in enabling autonomous driving, which is regarded as the significant key to unlocking the bottleneck of contemporary transportation systems from the perspectives of safety, mobility, and…

计算机视觉与模式识别 · 计算机科学 2023-02-08 Zhengwei Bai , Guoyuan Wu , Matthew J. Barth , Yongkang Liu , Emrah Akin Sisbot , Kentaro Oguchi

Thanks to the complementary nature of millimeter wave radar and camera, deep learning-based radar-camera 3D object detection methods may reliably produce accurate detections even in low-visibility conditions. This makes them preferable to…

计算机视觉与模式识别 · 计算机科学 2023-11-07 Irfan Tito Kurniawan , Bambang Riyanto Trilaksono

In a constant evolving world, change detection is of prime importance to keep updated maps. To better sense areas with complex geometry (urban areas in particular), considering 3D data appears to be an interesting alternative to classical…

计算机视觉与模式识别 · 计算机科学 2024-10-28 Iris de Gélis , Sébastien Lefèvre , Thomas Corpetti

Data augmentation is an effective regularization strategy to alleviate the overfitting, which is an inherent drawback of the deep neural networks. However, data augmentation is rarely considered for point cloud processing despite many…

计算机视觉与模式识别 · 计算机科学 2021-03-11 Dogyoon Lee , Jaeha Lee , Junhyeop Lee , Hyeongmin Lee , Minhyeok Lee , Sungmin Woo , Sangyoun Lee

3D shape recognition has attracted more and more attention as a task of 3D vision research. The proliferation of 3D data encourages various deep learning methods based on 3D data. Now there have been many deep learning models based on…

计算机视觉与模式识别 · 计算机科学 2020-03-02 Yaxin Zhao , Jichao Jiao , Tangkun Zhang

Point cloud analysis (such as 3D segmentation and detection) is a challenging task, because of not only the irregular geometries of many millions of unordered points, but also the great variations caused by depth, viewpoint, occlusion, etc.…

计算机视觉与模式识别 · 计算机科学 2023-07-28 Tuo Feng , Wenguan Wang , Xiaohan Wang , Yi Yang , Qinghua Zheng

Point cloud classification plays a crucial role in the processing and analysis of data from 3D sensors such as LiDAR, which are commonly used in applications like autonomous vehicles, robotics, and environmental monitoring. However,…

计算机视觉与模式识别 · 计算机科学 2025-01-16 Qiang Zheng , Chao Zhang , Jian Sun

3D object detection in point cloud data remains a challenging task due to the sparsity and lack of global structure inherent in the input. In this work, we propose a novel Multi-Scale Attention (MSA) mechanism integrated into the 3DETR…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Mustaqeem Khan , Aidana Nurakhmetova , Wail Gueaieb , Abdulmotaleb El Saddik

Recent developments in the field of deep learning for 3D data have demonstrated promising potential for end-to-end learning directly from point clouds. However, many real-world point clouds contain a large class im-balance due to the…

计算机视觉与模式识别 · 计算机科学 2019-06-19 David Griffiths , Jan Boehm

Domain adaptation methods for object detection (OD) strive to mitigate the impact of distribution shifts by promoting feature alignment across source and target domains. Multi-source domain adaptation (MSDA) allows leveraging multiple…

计算机视觉与模式识别 · 计算机科学 2024-12-13 Atif Belal , Akhil Meethal , Francisco Perdigon Romero , Marco Pedersoli , Eric Granger

3D object detection based on LiDAR point cloud and prior anchor boxes is a critical technology for autonomous driving environment perception and understanding. Nevertheless, an overlooked practical issue in existing methods is the ambiguity…

计算机视觉与模式识别 · 计算机科学 2024-03-05 Shitao Chen , Haolin Zhang , Nanning Zheng

Data augmentation improves the generalization power of deep learning models by synthesizing more training samples. Sample-mixing is a popular data augmentation approach that creates additional data by combining existing samples. Recent…

计算机视觉与模式识别 · 计算机科学 2024-03-20 Tsz-Him Cheung , Dit-Yan Yeung

Fusing LiDAR and camera information is essential for achieving accurate and reliable 3D object detection in autonomous driving systems. This is challenging due to the difficulty of combining multi-granularity geometric and semantic features…

计算机视觉与模式识别 · 计算机科学 2023-03-06 Yang Jiao , Zequn Jie , Shaoxiang Chen , Jingjing Chen , Lin Ma , Yu-Gang Jiang

Open set recognition (OSR) is devised to address the problem of detecting novel classes during model inference. Even in recent vision models, this remains an open issue which is receiving increasing attention. Thereby, a crucial challenge…

计算机视觉与模式识别 · 计算机科学 2025-05-20 Jiawen Xu , Odej Kao , Margret Keuper

High quality upsampling of sparse 3D point clouds is critically useful for a wide range of geometric operations such as reconstruction, rendering, meshing, and analysis. In this paper, we propose a data-driven algorithm that enables an…

计算机视觉与模式识别 · 计算机科学 2019-06-24 Wentai Zhang , Haoliang Jiang , Zhangsihao Yang , Soji Yamakawa , Kenji Shimada , Levent Burak Kara

3D object detection with LiDAR point clouds plays an important role in autonomous driving perception module that requires high speed, stability and accuracy. However, the existing point-based methods are challenging to reach the speed…

计算机视觉与模式识别 · 计算机科学 2021-10-13 Jiahui Fu , Guanghui Ren , Yunpeng Chen , Si Liu

Cooperative perception allows connected vehicles and roadside infrastructure to share sensor observations, creating a fused scene representation beyond the capability of any single platform. However, most cooperative 3D object detectors use…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Blessing Agyei Kyem , Joshua Kofi Asamoah , Armstrong Aboah

This paper investigates multi-scale feature approximation and transferable features for object detection from point clouds. Multi-scale features are critical for object detection from point clouds. However, multi-scale feature learning…

计算机视觉与模式识别 · 计算机科学 2025-08-19 Hao Peng , Hong Sang , Yajing Ma , Ping Qiu , Chao Ji