| 本文已被：浏览 1463次 下载 4386次 |
码上扫一扫！ |
|
|
| 分组并行的轻量化实时微观三维形貌重建方法 |
|
闫涛1,2,3, 高浩轩1,2, 张江峰1,2, 钱宇华1, 张临垣4
|
|
1.山西大学 大数据科学与产业研究院, 山西 太原 030006;2.山西大学 计算机与信息技术学院, 山西 太原 030006;3.哈尔滨工业大学 重庆研究院, 重庆 401151;4.北京中钞钞券设计制版有限公司, 北京 100070
|
|
| 摘要: |
| 微观三维形貌重建作为精密制造领域生产制造的关键环节,其重建过程依赖于高分辨率稠密图像的采集.而面对复杂应用场景的高时效性需求, 高分辨率稠密图像的输入会导致运算量与计算复杂度呈几何倍增加, 无法实现高效率低延时的实时微观三维形貌重建. 针对上述现状, 提出一种分组并行的轻量级实时微观三维形貌重建方法GPLWS-Net. GPLWS-Net以U型网络为基础构造轻量化主干网络, 以并行分组式查询加速三维形貌重建过程, 并针对神经网络结构进行重参数化设计避免重建微观结构的精度损失. 另外, 为弥补现有微观三维重建数据集的缺失, 公开了一组多聚焦微观三维重建数据集(Micro 3D), 其标签数据利用多模态数据融合的方式获取场景高精度的三维结构. 结果表明, 所提出的GPLWS-Net网络不仅可以保证重建精度, 而且在三组公开数据集中相比于其他5类深度学习方法平均耗时降低39.15%, 在Micro 3D数据集中平均耗时降低50.55%, 能够实现复杂微观场景的实时三维形貌重建. |
| 关键词: 微观三维形貌重建 轻量化神经网络 分组并行 |
| DOI：10.13328/j.cnki.jos.007013 |
| 分类号: |
| 基金项目:国家自然科学基金(62136005, 62006146); 科技创新2030—“新一代人工智能”重大项目(2021ZD0112400); 中央引导地方科技发展资金(YDZJSX20231C001, YDZJSX20231B001) |
|
| Grouping Parallel Lightweight Real-time Microscopic 3D Shape Reconstruction Method |
|
YAN Tao1,2,3, GAO Hao-Xuan1,2, ZHANG Jiang-Feng1,2, QIAN Yu-Hua1, ZHANG Lin-Yuan4
|
|
1.Institute of Big Data Science and Industry, Shanxi University, Taiyuan 030006, China;2.School of Computer and Information Technology, Shanxi University, Taiyuan 030006, China;3.Chongqing Research Institute of Harbin Institute of Technology, Harbin Institute of Technology, Chongqing 401151, China;4.Beijing Zhongchao Banknote Designing and Plate-making Co. Ltd., Beijing 100070, China
|
| Abstract: |
| Microscopic three-dimensional (3D) shape reconstruction is a crucial step in the field of precision manufacturing. The reconstruction process relies on the acquisition of high-resolution and dense images. Nevertheless, in the face of high efficiency requirements in complex application scenarios, inputting high-resolution dense images will result in geometrically increased computation and complexity, making it difficult to achieve efficient and low-latency real-time microscopic 3D shape reconstruction. In response to this situation, this study proposes a grouping parallelism lightweight real-time microscopic 3D shape reconstruction method GPLWS-Net. The GPLWS-Net constructs a lightweight backbone network based on a U-shaped network and accelerates the 3D shape reconstruction process with parallel group-querying. In addition, the neural network structure is re-parameterized to avoid the accuracy loss of reconstructing the microstructure. Furthermore, to supplement the lack of existing microscopic 3D reconstruction datasets, this study publicly releases a set of multi-focus microscopic 3D reconstruction dataset called Micro 3D. The label data uses multi-modal data fusion to obtain a high- precision 3D structure of the scene. The results show that the GPLWS-Net network can not only guarantee the reconstruction accuracy, but also reduce the average time of 39.15% in the three groups of public datasets and 50.55% in the Micro 3D dataset compared with the other five types of deep learning-based methods, which can achieve real-time 3D shape reconstruction of complex microscopic scenes. |
| Key words: microscopic 3D shape reconstruction lightweight neural network group parallelism |
