How Much Depth Information can Radar Contribute to a Depth Estimation Model?

TL;DR

This paper investigates the intrinsic depth information that radar data can provide for depth estimation models through inference and supervision experiments, showing radar's potential to contribute meaningful depth cues.

Contribution

It introduces radar inference and supervision experiments to quantify radar's intrinsic depth potential in monocular depth estimation models.

Findings

Radar-only models can partially detect surrounding shapes.

Radar-supervised models perform well compared to lidar-supervised baselines.

Radar provides valuable depth cues even when sparse.

Abstract

Recently, several works have proposed fusing radar data as an additional perceptual signal into monocular depth estimation models because radar data is robust against varying light and weather conditions. Although improved performances were reported in prior works, it is still hard to tell how much depth information radar can contribute to a depth estimation model. In this paper, we propose radar inference and supervision experiments to investigate the intrinsic depth potential of radar data using state-of-the-art depth estimation models on the nuScenes dataset. In the inference experiment, the model predicts depth by taking only radar as input to demonstrate the inference capability using radar data. In the supervision experiment, a monocular depth estimation model is trained under radar supervision to show the intrinsic depth information that radar can contribute. Our experiments demonstrate that the model using only sparse radar as input can detect the shape of surroundings to a certain extent in the predicted depth. Furthermore, the monocular depth estimation model supervised by preprocessed radar achieves a good performance compared to the baseline model trained with sparse lidar supervision.