当前位置: X-MOL 学术IEEE Trans. Instrum. Meas. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Incorporating Lambertian Priors Into Surface Normals Measurement
IEEE Transactions on Instrumentation and Measurement ( IF 5.6 ) Pub Date : 2021-07-12 , DOI: 10.1109/tim.2021.3096282
Yakun Ju , Muwei Jian , Shaoxiang Guo , Yingyu Wang , Huiyu Zhou , Junyu Dong

The goal of photometric stereo is to measure the precise surface normal of a 3-D object from observations with various shading cues. However, non-Lambertian surfaces influence the measurement accuracy due to irregular shading cues. Despite deep neural networks being used to simulate the performance of non-Lambertian surfaces, the error in specularities, shadows, and crinkle regions is hard to be reduced. To address this challenge, we here propose a photometric stereo network that incorporates Lambertian priors to better measure the surface normal. In this article, we use the initial normal under the Lambertian assumption as prior information to refine the normal measurement, instead of solely applying the observed shading cues to deriving the surface normal. Our method uses the Lambertian information to reparameterize the network weights and the powerful fitting ability of deep neural networks to correct these errors caused by general reflectance properties. Our explorations include: the Lambertian priors: 1) reduce the learning hypothesis space, making our method learn mapping in the same surface normal space and improving the accuracy of learning and 2) provides the differential features’ learning, improving the surfaces’ reconstruction of details. Extensive experiments verify the effectiveness of the proposed Lambertian prior photometric stereo network in accurate surface normal measurement, on the challenging benchmark dataset.

中文翻译:

将朗伯先验结合到表面法线测量中

光度立体的目标是从具有各种阴影线索的观察中测量 3-D 对象的精确表面法线。然而,由于不规则的阴影提示,非朗伯表面会影响测量精度。尽管使用深度神经网络来模拟非朗伯表面的性能,但很难减少镜面反射、阴影和皱纹区域的误差。为了应对这一挑战,我们在这里提出了一种光度立体网络,该网络结合了朗伯先验以更好地测量表面法线。在本文中,我们使用朗伯假设下的初始法线作为先验信息来改进法线测量,而不是仅应用观察到的阴影线索来推导表面法线。我们的方法使用朗伯信息来重新参数化网络权重,并利用深度神经网络的强大拟合能力来纠正由一般反射特性引起的这些错误。我们的探索包括:朗伯先验:1)减少学习假设空间,使我们的方法在相同的表面法线空间中学习映射并提高学习的准确性;2)提供微分特征的学习,改善表面对细节的重建. 在具有挑战性的基准数据集上,大量实验验证了所提出的朗伯先验光度立体网络在精确表面法线测量中的有效性。1)减少学习假设空间,使我们的方法在相同的表面法线空间学习映射,提高学习的准确性;2)提供微分特征的学习,提高表面对细节的重构。在具有挑战性的基准数据集上,大量实验验证了所提出的朗伯先验光度立体网络在精确表面法线测量中的有效性。1)减少学习假设空间,使我们的方法在相同的表面法线空间学习映射,提高学习的准确性;2)提供微分特征的学习,提高表面对细节的重构。在具有挑战性的基准数据集上,大量实验验证了所提出的朗伯先验光度立体网络在精确表面法线测量中的有效性。
更新日期:2021-07-27
down
wechat
bug