Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2503.16709 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913749458223104 |
|---|---|
| author | Shen, Xuan Ma, Weize Liu, Jing Yang, Changdi Ding, Rui Wang, Quanyi Ding, Henghui Niu, Wei Wang, Yanzhi Zhao, Pu Lin, Jun Gu, Jiuxiang |
| author_facet | Shen, Xuan Ma, Weize Liu, Jing Yang, Changdi Ding, Rui Wang, Quanyi Ding, Henghui Niu, Wei Wang, Yanzhi Zhao, Pu Lin, Jun Gu, Jiuxiang |
| contents | Monocular Depth Estimation (MDE) has emerged as a pivotal task in computer vision, supporting numerous real-world applications. However, deploying accurate depth estimation models on resource-limited edge devices, especially Application-Specific Integrated Circuits (ASICs), is challenging due to the high computational and memory demands. Recent advancements in foundational depth estimation deliver impressive results but further amplify the difficulty of deployment on ASICs. To address this, we propose QuartDepth which adopts post-training quantization to quantize MDE models with hardware accelerations for ASICs. Our approach involves quantizing both weights and activations to 4-bit precision, reducing the model size and computation cost. To mitigate the performance degradation, we introduce activation polishing and compensation algorithm applied before and after activation quantization, as well as a weight reconstruction method for minimizing errors in weight quantization. Furthermore, we design a flexible and programmable hardware accelerator by supporting kernel fusion and customized instruction programmability, enhancing throughput and efficiency. Experimental results demonstrate that our framework achieves competitive accuracy while enabling fast inference and higher energy efficiency on ASICs, bridging the gap between high-performance depth estimation and practical edge-device applicability. Code: https://github.com/shawnricecake/quart-depth |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_16709 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge Shen, Xuan Ma, Weize Liu, Jing Yang, Changdi Ding, Rui Wang, Quanyi Ding, Henghui Niu, Wei Wang, Yanzhi Zhao, Pu Lin, Jun Gu, Jiuxiang Computer Vision and Pattern Recognition Artificial Intelligence Monocular Depth Estimation (MDE) has emerged as a pivotal task in computer vision, supporting numerous real-world applications. However, deploying accurate depth estimation models on resource-limited edge devices, especially Application-Specific Integrated Circuits (ASICs), is challenging due to the high computational and memory demands. Recent advancements in foundational depth estimation deliver impressive results but further amplify the difficulty of deployment on ASICs. To address this, we propose QuartDepth which adopts post-training quantization to quantize MDE models with hardware accelerations for ASICs. Our approach involves quantizing both weights and activations to 4-bit precision, reducing the model size and computation cost. To mitigate the performance degradation, we introduce activation polishing and compensation algorithm applied before and after activation quantization, as well as a weight reconstruction method for minimizing errors in weight quantization. Furthermore, we design a flexible and programmable hardware accelerator by supporting kernel fusion and customized instruction programmability, enhancing throughput and efficiency. Experimental results demonstrate that our framework achieves competitive accuracy while enabling fast inference and higher energy efficiency on ASICs, bridging the gap between high-performance depth estimation and practical edge-device applicability. Code: https://github.com/shawnricecake/quart-depth |
| title | QuartDepth: Post-Training Quantization for Real-Time Depth Estimation on the Edge |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2503.16709 |