# CaR1: A Multi-Modal Baseline for BEV Vehicle Segmentation via Camera-Radar Fusion

Source: [CaR1: A Multi-Modal Baseline for BEV Vehicle Segmentation via Camera-Radar Fusion](<https://www.sota2.com/research/paper/68fa7b431e209131cea875c4>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:36:41.717Z

Authors: Santiago Montiel-Mar\\'in, Angel Llamazares, Miguel Antunes-Garc\\'ia, Fabio S\\'anchez-Garc\\'ia, Luis M. Bergasa

Published: 2025-09-12T11:07:56.000Z

## Abstract

Camera-radar fusion offers a robust and cost-effective alternative to LiDAR-based autonomous driving systems by combining complementary sensing capabilities: cameras provide rich semantic cues but unreliable depth, while radar delivers sparse yet reliable position and motion information. We introduce CaR1, a novel camera-radar fusion architecture for BEV vehicle segmentation. Built upon BEVFusion, our approach incorporates a grid-wise radar encoding that discretizes point clouds into structured BEV features and an adaptive fusion mechanism that dynamically balances sensor contributions. Experiments on nuScenes demonstrate competitive segmentation performance (57.6 IoU), on par with state-of-the-art methods. Code is publicly available \\href{https://www.github.com/santimontiel/car1}{online}.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2509.10139>)

[PDF](<https://arxiv.org/pdf/2509.10139.pdf>)
