轻量级雷达相机深度估计模型，通过知识蒸馏提升精度。
LiRCDepth: Lightweight Radar-Camera Depth Estimation via Knowledge Distillation and Uncertainty Guidance
- 用知识蒸馏将教师模型的特征与深度信息迁移至轻量学生模型。
- 在nuScenes数据集上MAE提升6.6%，优于无蒸馏训练的模型。
- 适合追求高效部署的自动驾驶多传感器系统开发者。
近期，雷达-相机融合算法受到广泛关注，因雷达传感器能提供补充相机局限性的几何信息。然而，多数现有雷达-相机深度估计方法仅关注性能提升，常忽视计算效率。为此，我们提出LiRCDepth，一种轻量级雷达-相机深度估计模型。通过知识蒸馏增强训练过程，将复杂教师模型的关键信息在三个关键领域迁移至轻量学生模型：首先，通过像素级与配对级蒸馏传递低层与高层特征；其次，引入不确定性感知的中间深度蒸馏损失，优化解码过程中的中间深度图。基于所提蒸馏方案，轻量模型在nuScenes数据集上的MAE相比无蒸馏训练的模型提升了6.6%。
原文摘要 · Abstract (English)
Recently, radar-camera fusion algorithms have gained significant attention as radar sensors provide geometric information that complements the limitations of cameras. However, most existing radar-camera depth estimation algorithms focus solely on improving performance, often neglecting computational efficiency. To address this gap, we propose LiRCDepth, a lightweight radar-camera depth estimation model. We incorporate knowledge distillation to enhance the training process, transferring critical information from a complex teacher model to our lightweight student model in three key domains. Firstly, low-level and high-level features are transferred by incorporating pixel-wise and pair-wise distillation. Additionally, we introduce an uncertainty-aware inter-depth distillation loss to refine intermediate depth maps during decoding. Leveraging our proposed knowledge distillation scheme, the lightweight model achieves a 6.6% improvement in MAE on the nuScenes dataset compared to the model trained without distillation. Code: https://github.com/harborsarah/LiRCDepth
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。