用雷达点云几何信息提升自动驾驶深度估计精度
GET-UP: GEomeTric-aware Depth Estimation with Radar Points UPsampling
- 用注意力图神经网络融合雷达2D与3D特征
- 通过激光雷达引导上采样增强点云密度和位置精度
- 在nuScenes数据集上比现有模型误差降低15%以上
深度估计在自动驾驶中至关重要，有助于全面理解车辆的三维环境。雷达因其在恶劣天气下的鲁棒性及测距能力，成为雷达-相机深度估计的研究热点。然而，现有方法将固有的噪声大、稀疏的雷达点云投影到图像平面进行像素级特征提取，忽略了点云中蕴含的宝贵几何信息。为此，本文提出GET-UP，利用注意力增强的图神经网络（GNN）交换并聚合雷达数据中的2D与3D信息，有效通过空间关系丰富特征表示，优于仅依赖2D特征提取的传统方法。此外，引入点云上采样任务，在激光雷达指导下对雷达点云进行稀疏化增强、位置校正，并提取额外3D特征。最后，在解码阶段融合雷达与相机特征完成深度估计。我们在nuScenes数据集上评估，GET-UP取得领先性能，相较之前最佳模型在MAE和RMSE上分别提升15.3%和14.7%。
原文摘要 · Abstract (English)
Depth estimation plays a pivotal role in autonomous driving, facilitating a comprehensive understanding of the vehicle's 3D surroundings. Radar, with its robustness to adverse weather conditions and capability to measure distances, has drawn significant interest for radar-camera depth estimation. However, existing algorithms process the inherently noisy and sparse radar data by projecting 3D points onto the image plane for pixel-level feature extraction, overlooking the valuable geometric information contained within the radar point cloud. To address this gap, we propose GET-UP, leveraging attention-enhanced Graph Neural Networks (GNN) to exchange and aggregate both 2D and 3D information from radar data. This approach effectively enriches the feature representation by incorporating spatial relationships compared to traditional methods that rely only on 2D feature extraction. Furthermore, we incorporate a point cloud upsampling task to densify the radar point cloud, rectify point positions, and derive additional 3D features under the guidance of lidar data. Finally, we fuse radar and camera features during the decoding phase for depth estimation. We benchmark our proposed GET-UP on the nuScenes dataset, achieving state-of-the-art performance with a 15.3% and 14.7% improvement in MAE and RMSE over the previously best-performing model. Code: https://github.com/harborsarah/GET-UP
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。