Photometric stereo is a technique aimed at determining surface normals through the utilization of shading cues derived from images taken under different lighting conditions. However, existing learning-based approaches often fail to accurately capture features at multiple stages and do not adequately promote interaction between these features. Consequently, these models tend to extract redundant features, especially in areas with intricate details such as wrinkles and edges. To tackle these issues, we propose MSF-Net, a novel framework for extracting information at multiple stages, paired with selective update strategy, aiming to extract high-quality feature information, which is critical for accurate normal construction. Additionally, we have developed a feature fusion module to improve the interplay among different features. Experimental results on the DiLiGenT benchmark show that our proposed MSF-Net significantly surpasses previous state-of-the-art methods in the accuracy of surface normal estimation.

翻译：光度立体是一种通过利用不同光照条件下拍摄图像中的阴影线索来确定表面法向的技术。然而，现有的基于学习的方法往往无法准确捕获多阶段特征，且未能充分促进这些特征间的交互。因此，这些模型倾向于提取冗余特征，尤其是在皱纹和边缘等细节复杂区域。为解决这些问题，我们提出了MSF-Net，一种新颖的多阶段信息提取框架，结合选择性更新策略，旨在提取高质量的特征信息，这对精确的法向重建至关重要。此外，我们开发了一个特征融合模块以增强不同特征间的相互作用。在DiLiGenT基准测试上的实验结果表明，我们提出的MSF-Net在表面法向估计的准确性上显著超越了先前的最先进方法。