arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.05367cs.CVcs.RO
收藏

重新思考用于LiDAR分割的Range View表示

Rethinking Range View Representation for LiDAR Segmentation

Shanghai AI Laboratory(上海人工智能实验室);National University of Singapore(新加坡国立大学);Hochschule Bremerhaven(不来梅哈芬应用技术大学);The University of Hong Kong(香港大学);ShanghaiTech University(上海科技大学);The Chinese University of Hong Kong(香港中文大学);Nanyang Technological University(南洋理工大学)

Lingdong Kong, Youquan Liu, Runnan Chen, Yuexin Ma, Xinge Zhu, Yikang Li, Yuenan Hou, Yu Qiao, Ziwei Liu

AI总结:

本文重新思考LiDAR分割中的range view表示,提出RangeFormer框架和STR训练策略,首次在多个基准上超越点、体素及多视图融合方法。

摘要:

LiDAR分割对于自动驾驶感知至关重要。最近的趋势倾向于基于点或体素的方法,因为它们通常比传统的range view表示产生更好的性能。在这项工作中,我们揭示了构建强大range view模型的几个关键因素。我们观察到“多对一”映射、语义不一致和形状变形可能是阻碍从range view投影进行有效学习的障碍。我们提出了RangeFormer——一个包含网络架构、数据增强和后处理方面新颖设计的全周期框架——它更好地处理了从range view对LiDAR点云的学习和过程。我们进一步引入了一种从range view的可扩展训练(STR)策略,该策略在任意低分辨率的2D range图像上训练,同时仍然保持令人满意的3D分割精度。我们表明,首次,一种range view方法能够在竞争性的LiDAR语义和全景分割基准(即SemanticKITTI、nuScenes和ScribbleKITTI)上超越点、体素和多视图融合对应方法。

英文摘要:

LiDAR segmentation is crucial for autonomous driving perception. Recent trends favor point- or voxel-based methods as they often yield better performance than the traditional range view representation. In this work, we unveil several key factors in building powerful range view models. We observe that the "many-to-one" mapping, semantic incoherence, and shape deformation are possible impediments against effective learning from range view projections. We present RangeFormer -- a full-cycle framework comprising novel designs across network architecture, data augmentation, and post-processing -- that better handles the learning and processing of LiDAR point clouds from the range view. We further introduce a Scalable Training from Range view (STR) strategy that trains on arbitrary low-resolution 2D range images, while still maintaining satisfactory 3D segmentation accuracy. We show that, for the first time, a range view method is able to surpass the point, voxel, and multi-view fusion counterparts in the competing LiDAR semantic and panoptic segmentation benchmarks, i.e., SemanticKITTI, nuScenes, and ScribbleKITTI.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑