We present a novel approach for metric dense depth estimation based on the
fusion of a single-view image and a sparse, noisy Radar point cloud. The direct
fusion of heterogeneous Radar and image data, or their encodings, tends to
yield dense depth maps with significant artifacts, blurred boundaries, and
suboptimal accuracy. To circumvent this issue, we learn to augment versatile
and robust monocular depth prediction with the dense metric scale induced from
sparse and noisy Radar data. We propose a Radar-Camera framework for highly
accurate and fine-detailed dense depth estimation with four stages, including
monocular depth prediction, global scale alignment of monocular depth with
sparse Radar points, quasi-dense scale estimation through learning the
association between Radar points and image patches, and local scale refinement
of dense depth using a scale map learner. Our proposed method significantly
outperforms the state-of-the-art Radar-Camera depth estimation methods by
reducing the mean absolute error (MAE) of depth estimation by 25.6% and 40.2%
on the challenging nuScenes dataset and our self-collected ZJU-4DRadarCam
dataset, respectively.

基于稀疏雷达点云和单视角图像的度量密集深度估计的新方法，使用雷达 — 相机框架对深度估计进行全局比例校准、稀疏雷达点与图像补丁的关联学习进行准密度尺度估计以及通过尺度映射学习对密集深度进行局部尺度细化，提高深度估计精度。在挑战性数据集 nuScenes 和自行收集的 ZJU-4DRadarCam 数据集上，与最先进的雷达 — 相机深度估计方法相比，我们提出的方法将深度估计的均方绝对误差 (MAE) 分别降低了 25.6% 和 40.2%。