Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.17335 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915168584204288 |
|---|---|
| author | Zhang, Xin Han, Liangxiu Sobeih, Tam Han, Lianghao Dancey, Darren |
| author_facet | Zhang, Xin Han, Liangxiu Sobeih, Tam Han, Lianghao Dancey, Darren |
| contents | Depth estimation is a critical task in computer vision, with applications in autonomous navigation, robotics, and augmented reality. Event cameras, which encode temporal changes in light intensity as asynchronous binary spikes, offer unique advantages such as low latency, high dynamic range, and energy efficiency. However, their unconventional spiking output and the scarcity of labelled datasets pose significant challenges to traditional image-based depth estimation methods. To address these challenges, we propose a novel energy-efficient Spike-Driven Transformer Network (SDT) for depth estimation, leveraging the unique properties of spiking data. The proposed SDT introduces three key innovations: (1) a purely spike-driven transformer architecture that incorporates spike-based attention and residual mechanisms, enabling precise depth estimation with minimal energy consumption; (2) a fusion depth estimation head that combines multi-stage features for fine-grained depth prediction while ensuring computational efficiency; and (3) a cross-modality knowledge distillation framework that utilises a pre-trained vision foundation model (DINOv2) to enhance the training of the spiking network despite limited data availability.This work represents the first exploration of transformer-based spiking neural networks for depth estimation, providing a significant step forward in energy-efficient neuromorphic computing for real-world vision applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_17335 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Novel Spike Transformer Network for Depth Estimation from Event Cameras via Cross-modality Knowledge Distillation Zhang, Xin Han, Liangxiu Sobeih, Tam Han, Lianghao Dancey, Darren Computer Vision and Pattern Recognition Artificial Intelligence Depth estimation is a critical task in computer vision, with applications in autonomous navigation, robotics, and augmented reality. Event cameras, which encode temporal changes in light intensity as asynchronous binary spikes, offer unique advantages such as low latency, high dynamic range, and energy efficiency. However, their unconventional spiking output and the scarcity of labelled datasets pose significant challenges to traditional image-based depth estimation methods. To address these challenges, we propose a novel energy-efficient Spike-Driven Transformer Network (SDT) for depth estimation, leveraging the unique properties of spiking data. The proposed SDT introduces three key innovations: (1) a purely spike-driven transformer architecture that incorporates spike-based attention and residual mechanisms, enabling precise depth estimation with minimal energy consumption; (2) a fusion depth estimation head that combines multi-stage features for fine-grained depth prediction while ensuring computational efficiency; and (3) a cross-modality knowledge distillation framework that utilises a pre-trained vision foundation model (DINOv2) to enhance the training of the spiking network despite limited data availability.This work represents the first exploration of transformer-based spiking neural networks for depth estimation, providing a significant step forward in energy-efficient neuromorphic computing for real-world vision applications. |
| title | A Novel Spike Transformer Network for Depth Estimation from Event Cameras via Cross-modality Knowledge Distillation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2404.17335 |