We present an automated machine learning approach for uncalibrated photometric stereo (PS). Our work aims at discovering lightweight and computationally efficient PS neural networks with excellent surface normal accuracy. Unlike previous uncalibrated deep PS networks, which are handcrafted and carefully tuned, we leverage differentiable neural architecture search (NAS) strategy to find uncalibrated PS architecture automatically. We begin by defining a discrete search space for a light calibration network and a normal estimation network, respectively. We then perform a continuous relaxation of this search space and present a gradient-based optimization strategy to find an efficient light calibration and normal estimation network. Directly applying the NAS methodology to uncalibrated PS is not straightforward as certain task-specific constraints must be satisfied, which we impose explicitly. Moreover, we search for and train the two networks separately to account for the Generalized Bas-Relief (GBR) ambiguity. Extensive experiments on the DiLiGenT dataset show that the automatically searched neural architectures performance compares favorably with the state-of-the-art uncalibrated PS methods while having a lower memory footprint.
翻译:我们为未经校准的光度测光立体(PS)提出了一个自动机器学习方法。 我们的工作旨在发现光量和计算高效的PS神经网络,其表面正常精确度很高。 与以前未经校准的深PS网络不同,这些网络是手工制作的,经过仔细调整,我们利用不同的神经结构搜索(NAS)战略来自动找到未经校准的PS结构。 我们首先为光度校准网络和正常估测网络分别确定一个离散搜索空间。 然后我们持续放松这一搜索空间,并推出一个基于梯度的优化战略,以找到高效的光度校准和正常估测网络。 直接将NAS方法应用于未经校准的PS并不是直接的,因为某些特定任务的限制必须得到满足。 此外,我们搜索和培训这两个网络是分别考虑通用的Bas-Relief(GBR)模糊性的。 在DiGenT数据设置上进行的广泛实验显示,自动搜索的神经结构的性能优于具有较低历史足迹的状态。