TRIDE: A Text-assisted Radar-Image weather-aware fusion network for Depth Estimation

TL;DR

TRIDE introduces a weather-aware radar-camera fusion network that leverages text descriptions and radar data to improve depth estimation accuracy in autonomous driving, especially under adverse weather conditions.

Contribution

The paper proposes a novel weather-aware fusion block and text-assisted feature extraction method for improved depth estimation in radar-camera systems.

Findings

Achieves 12.87% improvement in MAE on nuScenes dataset.

Achieves 9.08% improvement in RMSE on nuScenes dataset.

Demonstrates robustness of the approach under different weather conditions.

Abstract

Depth estimation, essential for autonomous driving, seeks to interpret the 3D environment surrounding vehicles. The development of radar sensors, known for their cost-efficiency and robustness, has spurred interest in radar-camera fusion-based solutions. However, existing algorithms fuse features from these modalities without accounting for weather conditions, despite radars being known to be more robust than cameras under adverse weather. Additionally, while Vision-Language models have seen rapid advancement, utilizing language descriptions alongside other modalities for depth estimation remains an open challenge. This paper first introduces a text-generation strategy along with feature extraction and fusion techniques that can assist monocular depth estimation pipelines, leading to improved accuracy across different algorithms on the KITTI dataset. Building on this, we propose TRIDE, a radar-camera fusion algorithm that enhances text feature extraction by incorporating radar point information. To address the impact of weather on sensor performance, we introduce a weather-aware fusion block that adaptively adjusts radar weighting based on current weather conditions. Our method, benchmarked on the nuScenes dataset, demonstrates performance gains over the state-of-the-art, achieving a 12.87% improvement in MAE and a 9.08% improvement in RMSE. Code: https://github.com/harborsarah/TRIDE