# RCDINO: Enhancing Radar-Camera 3D Object Detection with DINOv2 Semantic Features

Source: [RCDINO: Enhancing Radar-Camera 3D Object Detection with DINOv2 Semantic Features](<https://www.sota2.com/research/paper/68fa7ad41e209131cea8560a>)

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

Data updated: 2025-10-27T07:00:40.261Z

Authors: Olga Matykina, Dmitry Yudin

Published: 2025-08-21T08:33:36.000Z

## Abstract

Three-dimensional object detection is essential for autonomous driving and robotics, relying on effective fusion of multimodal data from cameras and radar. This work proposes RCDINO, a multimodal transformer-based model that enhances visual backbone features by fusing them with semantically rich representations from the pretrained DINOv2 foundation model. This approach enriches visual representations and improves the model's detection performance while preserving compatibility with the baseline architecture. Experiments on the nuScenes dataset demonstrate that RCDINO achieves state-of-the-art performance among radar-camera models, with 56.4 NDS and 48.1 mAP. Our implementation is available at https://github.com/OlgaMatykina/RCDINO.

## 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/2508.15353>)

[PDF](<https://arxiv.org/pdf/2508.15353.pdf>)