通过多范围图像训练提升激光雷达语义分割精度与速度
FLARES: Fast and Accurate LiDAR Multi-Range Semantic Segmentation
- 将点云分段生成多范围视图，增强信息保留
- 在SemanticKITTI上提升2.1%~7.9% mIoU，nuScenes上1.8%~3.9% mIoU
- 适合追求高效高精度3D感知的自动驾驶系统
三维场景理解在自动驾驶中至关重要但极具挑战，源于激光雷达数据的不规则性和稀疏性，以及处理大规模点云的计算压力。现有方法采用范围视图表示以提升效率，但常通过提高方位分辨率来缓解球面投影中的信息丢失（仅保留每个二维网格最近点）。然而，处理宽幅全景范围视图仍效率低下，并可能引入额外畸变。我们实证分析表明，通过分割完整点云生成多个范围图像进行训练，可同时提升分割精度与计算效率。但该方法也加剧了类别不平衡和投影伪影问题。为此，我们提出FLARES，一种新颖的训练范式，包含两种定制数据增强技术及针对多范围设置设计的专用后处理方法。大量实验表明，FLARES在不同架构间高度泛化，在SemanticKITTI上实现2.1%~7.9% mIoU提升，在nuScenes上实现1.8%~3.9% mIoU提升，推理速度提升超过40%。
原文摘要 · Abstract (English)
3D scene understanding is a critical yet challenging task in autonomous driving due to the irregularity and sparsity of LiDAR data, as well as the computational demands of processing large-scale point clouds. Recent methods leverage range-view representations to enhance efficiency, but they often adopt higher azimuth resolutions to mitigate information loss during spherical projection, where only the closest point is retained for each 2D grid. However, processing wide panoramic range-view images remains inefficient and may introduce additional distortions. Our empirical analysis shows that training with multiple range images, obtained from splitting the full point cloud, improves both segmentation accuracy and computational efficiency. However, this approach also poses new challenges of exacerbated class imbalance and increase in projection artifacts. To address these, we introduce FLARES, a novel training paradigm that incorporates two tailored data augmentation techniques and a specialized post-processing method designed for multi-range settings. Extensive experiments demonstrate that FLARES is highly generalizable across different architectures, yielding 2.1%~7.9% mIoU improvements on SemanticKITTI and 1.8%~3.9% mIoU on nuScenes, while delivering over 40% speed-up in inference.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。