3D Reconstruction of Ancient Buildings Using UAV Images and Neural Radiation Field with Depth Supervision

Abstract

The 3D reconstruction of ancient buildings through inclined photogrammetry finds a wide range of applications in surveying, visualization and heritage conservation. Unlike indoor objects, reconstructing ancient buildings presents unique challenges, including the slow speed of 3D reconstruction using traditional methods, the complex textures of ancient structures and geometric issues caused by repeated textures. Additionally, there is a hash conflict problem when rendering outdoor scenes using neural radiation fields. To address these challenges, this paper proposes a 3D reconstruction method based on depth-supervised neural radiation fields. To enhance the representation of the geometric neural network, the addition of a truncated signed distance function (TSDF) supplements the existing signed distance function (SDF). Furthermore, the neural network’s training is supervised using depth information, leading to improved geometric accuracy in the reconstruction model through depth data obtained from sparse point clouds. This study also introduces a progressive training strategy to mitigate hash conflicts, allowing the hash table to express important details more effectively while reducing feature overlap. The experimental results demonstrate that our method, under the same number of iterations, produces images with clearer structural details, resulting in an average 15% increase in the Peak Signal-to-Noise Ratio (PSNR) value and a 10% increase in the Structural Similarity Index Measure (SSIM) value. Moreover, our reconstruction model produces higher-quality surface models, enabling the fast and highly geometrically accurate 3D reconstruction of ancient buildings.

Advanced enhancement technique for infrared images of wind turbine blades utilizing adaptive difference multi-scale top-hat transformation

“…Structural similarity (SSIM) 41 is a metric between 0 and 1 used to evaluate the similarity between two images. A higher SSIM value indicates less difference between the two images, implying that the image enhancement method applied can better preserve the structural details of the image, resulting in improved visual effects.…”

Quasi-Dense Matching for Oblique Stereo Images through Semantic Segmentation and Local Feature Enhancement

“…In recent years, obtaining high-resolution multiview images of ground scenes has become increasingly easier with the development of ground mobile wide-baseline photography, UAV oblique photography, and other technologies [1]. However, under large viewpoint conditions, substantial changes in the main optical axis can lead to substantial distortions or masking in the scale, orientation, surface brightness, and neighborhood information of the same spatial target in stereo images.…”