用DINOv2语义特征增强雷达-相机3D检测，性能领先
RCDINO: Enhancing Radar-Camera 3D Object Detection with DINOv2 Semantic Features
- 融合DINOv2预训练语义特征，提升视觉主干表征能力
- 在nuScenes上达到56.4 NDS和48.1 mAP，刷新雷达-相机模型纪录
- 无需改动基线架构，适配自动驾驶与机器人感知系统
三维目标检测对自动驾驶和机器人至关重要，依赖于摄像头与雷达的多模态数据融合。本文提出RCDINO，一种基于Transformer的多模态模型，通过将预训练DINOv2模型提供的语义丰富表征与视觉主干特征融合，增强视觉表示并提升检测性能，同时保持与基线架构的兼容性。在nuScenes数据集上的实验表明，RCDINO在雷达-相机模型中达到当前最优性能，实现56.4 NDS和48.1 mAP。代码已开源：https://github.com/OlgaMatykina/RCDINO。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。