用全景深度图提升自动驾驶3D感知精度
Omnidirectional Depth-Aided Occupancy Prediction based on Cylindrical Voxel for Autonomous Driving
- 基于柱面体素表示，匹配全景相机的环形视角
- 提出Sketch-Coloring框架，显著提升3D占用预测性能
- 构建双倍于SemanticKITTI的虚拟鱼眼数据集
精准的3D感知对自动驾驶至关重要。传统方法因缺乏几何先验，常面临几何模糊问题。为此，本文利用全景深度估计引入几何先验，提出Sketch-Coloring框架OmniDepth-Occ。基于深度信息，设计了基于极坐标系的柱面体素表示，更契合全景相机的径向视图特性。针对自动驾驶中鱼眼相机数据集匮乏的问题，构建了一个包含六个鱼眼相机的虚拟场景数据集，数据量达SemanticKITTI的两倍。实验表明，所提网络显著提升了3D感知性能。
原文摘要 · Abstract (English)
Accurate 3D perception is essential for autonomous driving. Traditional methods often struggle with geometric ambiguity due to a lack of geometric prior. To address these challenges, we use omnidirectional depth estimation to introduce geometric prior. Based on the depth information, we propose a Sketch-Coloring framework OmniDepth-Occ. Additionally, our approach introduces a cylindrical voxel representation based on polar coordinate to better align with the radial nature of panoramic camera views. To address the lack of fisheye camera dataset in autonomous driving tasks, we also build a virtual scene dataset with six fisheye cameras, and the data volume has reached twice that of SemanticKITTI. Experimental results demonstrate that our Sketch-Coloring network significantly enhances 3D perception performance.
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。