JustDepth: Real-Time Radar-Camera Depth Estimation with Single-Scan LiDAR Supervision
Abstract
Accurate yet low-latency depth is essential for radar-camera perception in autonomous systems. Cameras provide rich appearance but lack metric scale, whereas automotive radar offers metric range but is sparse and noisy. Many pipelines are multi-stage or depend on auxiliary annotations, increasing latency and limiting portability. We introduce JustDepth, a single-stage radar-camera depth estimator trained only with radar, camera, and single-scan LiDAR. All radar returns are aggregated into a fixed-width 1D representation, decoupling runtime from point count. A Height Fusion Block fuses modalities, a lightweight GNN propagates depth globally, and a training-only confidence decoder stabilizes learning with zero test-time cost. We mitigate stripe artifacts via simple augmentations and quantify them using the Vertical-Horizontal Gradient Ratio (VHGR). On nuScenes, compared to recent state-of-the-art methods, JustDepth maintains accuracy while reducing inference time by 39.7x and stripe artifacts by 66% as measured by VHGR.
Cite
@article{arxiv.2607.22172,
title = {JustDepth: Real-Time Radar-Camera Depth Estimation with Single-Scan LiDAR Supervision},
author = {Wooyung Yun and Dongwook Kim and Soomok Lee},
journal= {arXiv preprint arXiv:2607.22172},
year = {2026}
}
Comments
Project page: https://github.com/TPyun/JustDepth