基于圆柱体素的全向深度辅助占用预测用于自动驾驶
Omnidirectional Depth-Aided Occupancy Prediction based on Cylindrical Voxel for Autonomous Driving
AI总结：
针对自动驾驶3D感知的几何模糊问题，提出基于圆柱体素和全向深度估计的Sketch-Coloring框架OmniDepth-Occ，并构建大规模鱼眼相机数据集，显著提升了3D感知性能。
摘要：
准确的3D感知对自动驾驶至关重要。传统方法常因缺乏几何先验而难以解决几何模糊性。为应对这些挑战，我们利用全向深度估计引入几何先验。基于深度信息，我们提出了Sketch-Coloring框架OmniDepth-Occ。此外，我们的方法引入了基于极坐标的圆柱体素表示，以更好匹配全景相机视图的径向特性。为解决自动驾驶任务中缺乏鱼眼相机数据集的问题，我们还构建了一个包含六个鱼眼相机的虚拟场景数据集，其数据量已达到SemanticKITTI的两倍。实验结果表明，我们的Sketch-Coloring网络显著提升了3D感知性能。
英文摘要：
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.
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。
