返回
GPU Rasterization-Based 3D LiDAR Simulation for Deep Learning
DOI:10.3390/s23198130.png)
摘要
En 中文
High-quality data are of utmost importance for any deep-learning application. However, acquiring such data and their annotation is challenging. This paper presents a GPU-accelerated simulator that enables the generation of high-quality, perfectly labelled data for any Time-of-Flight sensor, including LiDAR. Our approach optimally exploits the 3D graphics pipeline of the GPU, significantly decreasing data generation time while preserving compatibility with all real-time rendering engines. The presented algorithms are generic and allow users to perfectly mimic the unique sampling pattern of any such sensor. To validate our simulator, two neural networks are trained for denoising and semantic segmentation. To bridge the gap between reality and simulation, a novel loss function is introduced that requires only a small set of partially annotated real data. It enables the learning of classes for which no labels are provided in the real data, hence dramatically reducing annotation efforts. With this work, we hope to provide means for alleviating the data acquisition problem that is pertinent to deep-learning applications.
Keyword:
LiDAR
GPU
simulation
data generation
neural networks
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.5
论文数:
7.3W
被引数:
26.5W
机构
引用论文
Determinants of quality of life in patients with fibromyalgia: A structural equation modeling approach纤维肌痛患者生活质量的决定因素: 结构方程建模方法
PLOS ONE
IF0
No posterior mandibular displacement in Angle Class II, division 2 malocclusion as revealed with electromyography and sirognathographyAngle Class II, division 2错𬌗关系中无后部下颌位移,如经肌电图和sirognathography揭示。

