Surface Reconstruction Assessment in Photogrammetric Applications

Abstract

The image-based 3D reconstruction pipeline aims to generate complete digital representations of the recorded scene, often in the form of 3D surfaces. These surfaces or mesh models are required to be highly detailed as well as accurate enough, especially for metric applications. Surface generation can be considered as a problem integrated in the complete 3D reconstruction workflow and thus visibility information (pixel similarity and image orientation) is leveraged in the meshing procedure contributing to an optimal photo-consistent mesh. Other methods tackle the problem as an independent and subsequent step, generating a mesh model starting from a dense 3D point cloud or even using depth maps, discarding input image information. Out of the vast number of approaches for 3D surface generation, in this study, we considered three state of the art methods. Experiments were performed on benchmark and proprietary datasets of varying nature, scale, shape, image resolution and network designs. Several evaluation metrics were introduced and considered to present qualitative and quantitative assessment of the results.

HUMANNET—A Two-Tiered Deep Neural Network Architecture for Self-Occluding Humanoid Pose Reconstruction

“…While the majority of methods focus on voxel based mesh representation [22][23][24][25][26][27], for object reconstruction due to their representation simplicity, voxels have one major flaw-exponentially increasing requirements to train them with increasing fidelity. Some papers tried to solve this ever-increasing memory requirements using smarter data representation styles like octrees [28,29].…”

Surface Reconstruction from Structured Light Images Using Differentiable Rendering

“…Our method has three major implications: (1) explicit point triangulation from image correspondences is no longer needed; (2) we understand how noise in the image data affects the final reconstruction; and (3) the reconstruction is done for all image data simultaneously. Starting from a sphere, our method reconstructs the Stanford Bunny [3] from images with low levels of noise.…”

“…The resulting mesh is a digital representation of the surface of the scanned object. This has many applications, including cultural heritage preservation and industrial quality control [ 1 , 2 ]. For most applications, the accuracy of the recovered surface of the reconstruction is of great importance.…”

Graphic Applications of Unmanned Aerial Vehicles (UAVs) in the Study of Industrial Heritage Assets

“…Photogrammetry techniques are widely employed in different disciplines: architecture, topography, archaeology and cartography are some examples [25][26][27]. These techniques aim to calculate the dimensions and positions of objects in space, from measurements made with photographs.…”