BEV-CAR：以上下文感知光栅化增强单目鸟瞰图分割
BEV-CAR: Enhancing Monocular Bird's Eye View Segmentation with Context-Aware Rasterization
提出一种无需坐标变换的上下文感知光栅化方式，直接在BEV表示上逐条光线优化并注入深度特征，可被单目BEV分割/检测流水线复用，用于缓解遮挡区域的前景与布局估计误差，且推理阶段零额外开销。
原文依据 a Context-Aware Rasterization method that rasterizes the BEV representation without any coordinate transformations
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论鸟瞰图（BEV）语义分割对自动驾驶与移动机器人至关重要，但在前景目标的准确分割以及被物体遮挡的布局类别的有效估计方面仍面临显著挑战。为解决这些问题，我们提出 BEV-CAR，一种上下文感知光栅化方法，它在不进行任何坐标变换的情况下对 BEV 表示进行光栅化。通过优化每条光线并引入深度特征，BEV-CAR 有效应对了物体遮挡与多变环境条件带来的挑战。它在多种场景下保持稳健性能，尤其提升了遮挡区域中前景目标分割与布局估计的准确度。在 nuScenes 与 Argoverse 数据集上的大量实验表明，BEV-CAR 取得了最优（SOTA）性能。更重要的是，本文的光栅化技术在推理过程中不引入额外计算开销，因而适合真实场景中的实际部署。代码见 https://github.com/BEV-DAR/BEV-DAR。
英文原文摘要 1155 字符
Bird's Eye View (BEV) semantic segmentation is essential for autonomous driving and mobile robotics, yet it still faces significant challenges on accurate segmentation of foreground object and efficient estimating of layout categories obscured by objects. To address these issues, we propose BEV-CAR, a Context-Aware Rasterization method that rasterizes the BEV representation without any coordinate transformations. By optimising each ray and incorporating depth features, BEV-CAR effectively addresses the challenges posed by object occlusions and varying environmental conditions. It ensures robust performance across diverse scenarios, particularly improving the accuracy of foreground object segmentation and layout estimation in occluded areas. And extensive experiments on the nuScenes and Argoverse datasets demonstrate that BEV-CAR achieves state-of-the-art (SOTA) performance. More importantly, the rasterization technique in this paper does not introduce additional computational overhead during the inference process, making it suitable for practical deployment in real-world scenarios. Code is available in https://github.com/BEV-DAR/BEV-DAR.