• 首页
  • 期刊简介
  • 编委会
  • 投稿指南
  • 收录情况
  • 杂志订阅
  • 联系我们
引用本文:方明权,宋 滢.基于深度学习和自注意力的光度立体方法[J].软件工程,2024,(8):46-50.【点击复制】
【打印本页】   【下载PDF全文】   【查看/发表评论】  【下载PDF阅读器】  
←前一篇|后一篇→ 过刊浏览
分享到: 微信 更多
基于深度学习和自注意力的光度立体方法
方明权, 宋 滢
(浙江理工大学信息科学与工程学院, 浙江 杭州 310018)
fangmingquan7@163.com; ysong@zstu.edu.cn
摘 要: 针对基于深度学习的非标定光度立体方法,设计了一种基于自注意力和多重特征融合的网络模型。该模型在光照估计网络中引入了自注意力机制,用于帮助网络理解图像长距离像素间的依赖关系,提升网络对图像深层特征的感知能力。同时,为了提升在多图像输入时的特征融合效果,设计了一种基于多重最大池化和残差模块的法线恢复网络。该方法在DiLiGenT光度立体数据集上测试的光源方向和法向的平均角度误差分别为3.2和8.5。
关键词: 光度立体;深度学习;自注意力;残差网络
中图分类号: TP389.1    文献标识码: A
Photometric Stereo Method Based on Deep Learning and Self-Attention Mechanism
FANG Mingquan, SONG Ying
(School of In f ormation Science and Engineering, Zhejiang Sci-Tech University, Hangzhou 310018, China)
fangmingquan7@163.com; ysong@zstu.edu.cn
Abstract: In response to deep learning-based uncalibrated photometric stereo method, this paper proposes a network model based on self-attention and multi-feature fusion. This model introduces a self-attention mechanism into the illumination estimation network to help the network understand the long-range pixel dependencies in images, enhancing the network's perception of deep image features. Additionally, to improve the feature fusion effect when multiple images are input, a normal recovery network based on multiple max-pooling and residual modules is designed. The proposed method achieves average angular errors of 3.2 for light source direction and 8.5 for surface normal on the DiLiGenT photometric stereo dataset.
Keywords: photometric stereo; deep learning; self-attention; residual network


版权所有:软件工程杂志社
地址:辽宁省沈阳市浑南区新秀街2号 邮政编码:110179
电话:0411-84767887 传真:0411-84835089 Email:semagazine@neusoft.edu.cn
备案号:辽ICP备17007376号-1
技术支持:北京勤云科技发展有限公司

用微信扫一扫

用微信扫一扫