轮廓仪
深度学习
计算机科学
人工智能
人工神经网络
功能(生物学)
航程(航空)
模式识别(心理学)
计算机视觉
表面光洁度
工程类
进化生物学
机械工程
生物
航空航天工程
作者
Sam Van der Jeught,Pieter G.G. Muyshondt,Iván Lobato
出处
期刊:JPhys photonics
[IOP Publishing]
日期:2021-03-18
卷期号:3 (2): 024014-024014
被引量:14
标识
DOI:10.1088/2515-7647/abf030
摘要
Abstract Single-shot structured light profilometry (SLP) aims at reconstructing the 3D height map of an object from a single deformed fringe pattern and has long been the ultimate goal in fringe projection profilometry. Recently, deep learning was introduced into SLP setups to replace the task-specific algorithm of fringe demodulation with a dedicated neural network. Research on deep learning-based profilometry has made considerable progress in a short amount of time due to the rapid development of general neural network strategies and to the transferrable nature of deep learning techniques to a wide array of application fields. The selection of the employed loss function has received very little to no attention in the recently reported deep learning-based SLP setups. In this paper, we demonstrate the significant impact of loss function selection on height map prediction accuracy, we evaluate the performance of a range of commonly used loss functions and we propose a new mixed gradient loss function that yields a higher 3D surface reconstruction accuracy than any previously used loss functions.
科研通智能强力驱动
Strongly Powered by AbleSci AI