LiRCDepth: Lightweight Radar-Camera Depth Estimation via Knowledge Distillation and Uncertainty Guidance
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929648098607104 |
|---|---|
| author | Sun, Huawei Vysotskaya, Nastassia Sukianto, Tobias Feng, Hao Ott, Julius Peng, Xiangyuan Servadei, Lorenzo Wille, Robert |
| author_facet | Sun, Huawei Vysotskaya, Nastassia Sukianto, Tobias Feng, Hao Ott, Julius Peng, Xiangyuan Servadei, Lorenzo Wille, Robert |
| contents | 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_16380 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LiRCDepth: Lightweight Radar-Camera Depth Estimation via Knowledge Distillation and Uncertainty Guidance Sun, Huawei Vysotskaya, Nastassia Sukianto, Tobias Feng, Hao Ott, Julius Peng, Xiangyuan Servadei, Lorenzo Wille, Robert Computer Vision and Pattern Recognition Image and Video Processing 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 |
| title | LiRCDepth: Lightweight Radar-Camera Depth Estimation via Knowledge Distillation and Uncertainty Guidance |
| topic | Computer Vision and Pattern Recognition Image and Video Processing |
| url | https://arxiv.org/abs/2412.16380 |