融合神经网络与优化的4D雷达里程计，提升稀疏点云定位精度。
DNOI-4DRO: Deep 4D Radar Odometry with Differentiable Neural-Optimization Iterations
- 用神经网络估计点运动流，再通过可微优化迭代精修姿态。
- 在VoD和Snail-Radar数据集上优于主流方法，接近激光雷达性能。
- 适合自动驾驶中雷达感知场景，尤其点云稀疏时表现突出。
本文提出一种新型学习-优化融合的4D雷达里程计模型DNOI-4DRO。该模型将传统几何优化与端到端神经网络训练无缝结合，引入创新的可微神经-优化迭代算子。首先通过神经网络估计点级运动流，随后基于点运动与姿态在三维空间中的关系构建代价函数，并采用高斯-牛顿更新进行雷达位姿精化。此外，设计双流4D雷达骨干网络，融合多尺度几何特征与聚类引导的类别感知特征，增强稀疏4D雷达点云表征能力。在VoD和Snail-Radar数据集上的大量实验表明，本模型性能显著优于近期经典与学习型方法，甚至在输入为激光雷达点云时达到与A-LOAM相当的定位效果。模型代码将公开发布。
原文摘要 · Abstract (English)
A novel learning-optimization-combined 4D radar odometry model, named DNOI-4DRO, is proposed in this paper. The proposed model seamlessly integrates traditional geometric optimization with end-to-end neural network training, leveraging an innovative differentiable neural-optimization iteration operator. In this framework, point-wise motion flow is first estimated using a neural network, followed by the construction of a cost function based on the relationship between point motion and pose in 3D space. The radar pose is then refined using Gauss-Newton updates. Additionally, we design a dual-stream 4D radar backbone that integrates multi-scale geometric features and clustering-based class-aware features to enhance the representation of sparse 4D radar point clouds. Extensive experiments on the VoD and Snail-Radar datasets demonstrate the superior performance of our model, which outperforms recent classical and learning-based approaches. Notably, our method even achieves results comparable to A-LOAM with mapping optimization using LiDAR point clouds as input. Our models and code will be publicly released.
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。