Nowadays, three-dimensional reconstruction is used in various fields like
computer vision, computer graphics, mixed reality and digital twin. The
three-dimensional reconstruction of cultural heritage objects is one of the
most important applications in this area which is usually accomplished by close
range photogrammetry. The problem here is that the images are often noisy, and
the dense image matching method has significant limitations to reconstruct the
geometric details of cultural heritage objects in practice. Therefore,
displaying high-level details in three-dimensional models, especially for
cultural heritage objects, is a severe challenge in this field. In this paper,
the shape from polarization method has been investigated, a passive method with
no drawbacks of active methods. In this method, the resolution of the depth
maps can be dramatically increased using the information obtained from the
polarization light by rotating a linear polarizing filter in front of a digital
camera. Through these polarized images, the surface details of the object can
be reconstructed locally with high accuracy. The fusion of polarization and
photogrammetric methods is an appropriate solution for achieving high
resolution three-dimensional reconstruction. The surface reconstruction
assessments have been performed visually and quantitatively. The evaluations
showed that the proposed method could significantly reconstruct the surfaces'
details in the three-dimensional model compared to the photogrammetric method
with 10 times higher depth resolution.

通过极化方法，结合摄影测量方法，可以获得高分辨率的文化遗产物体的三维重建，相比摄影测量方法提高了 10 倍的深度分辨率。

文化遗产物体的高分辨率表面重建：基于极化法的形状提取

High Resolution Surface Reconstruction of Cultural Heritage Objects  Using Shape from Polarization Method

Monocular depth estimation, which plays a key role in understanding 3D scene
geometry, is fundamentally an ill-posed problem. Existing methods based on deep
convolutional neural networks (DCNNs) have examined this problem by learning
convolutional networks to estimate continuous depth maps from monocular images.
However, we find that training a network to predict a high spatial resolution
continuous depth map often suffers from poor local solutions. In this paper, we
hypothesize that achieving a compromise between spatial and depth resolutions
can improve network training. Based on this "compromise principle", we propose
a regression-classification cascaded network (RCCN), which consists of a
regression branch predicting a low spatial resolution continuous depth map and
a classification branch predicting a high spatial resolution discrete depth
map. The two branches form a cascaded structure allowing the classification and
regression branches to benefit from each other. By leveraging large-scale raw
training datasets and some data augmentation strategies, our network achieves
top or state-of-the-art results on the NYU Depth V2, KITTI, and Make3D
benchmarks.

本文提出了一种基于回归和分类级联的网络，利用大规模训练数据和数据增强策略，在空间和深度分辨率之间寻求平衡，提高了网络的训练效果，在 NYU Depth V2、KITTI、Make3D 等基准测试中均取得了最佳或最先进的结果。