Skip to main content

2020 | Buch

Advances in Photometric 3D-Reconstruction

herausgegeben von: Assoc. Prof. Jean-Denis Durou, Prof. Maurizio Falcone, Dr. Yvain Quéau, Dr. Silvia Tozza

Verlag: Springer International Publishing

Buchreihe : Advances in Pattern Recognition

insite
SUCHEN

Über dieses Buch

This book presents the latest advances in photometric 3D reconstruction. It provides the reader with an overview of the state of the art in the field, and of the latest research into both the theoretical foundations of photometric 3D reconstruction and its practical application in several fields (including security, medicine, cultural heritage and archiving, and engineering). These techniques play a crucial role within such emerging technologies as 3D printing, since they permit the direct conversion of an image into a solid object.

The book covers both theoretical analysis and real-world applications, highlighting the importance of deepening interdisciplinary skills, and as such will be of interest to both academic researchers and practitioners from the computer vision and mathematical 3D modeling communities, as well as engineers involved in 3D printing. No prior background is required beyond a general knowledge of classical computer vision models, numerical methods for optimization, and partial differential equations.

Inhaltsverzeichnis

Frontmatter
Chapter 1. A Comprehensive Introduction to Photometric 3D-Reconstruction
Abstract
Photometric 3D-reconstruction techniques aim at inferring the geometry of a scene from one or several images, by inverting a physical model describing the image formation. This chapter presents an introductory overview of the main photometric 3D-reconstruction techniques which are shape-from-shading, photometric stereo and shape-from-polarisation.
Jean-Denis Durou, Maurizio Falcone, Yvain Quéau, Silvia Tozza
Chapter 2. Perspective Shape from Shading
An Exposition on Recent Works with New Experiments
Abstract
Shape from Shading (SFS) is a fundamental task in computer vision. By given information about the reflectance of an object’s surface and the position of the light source, the SFS problem is to reconstruct the 3D depth of the object from a single grayscale 2D input image. A modern class of SFS models relies on the property that the camera performs a perspective projection. The corresponding perspective SFS methods have been the subject of many investigations within the last years. The goal of this chapter is to give an overview of these developments. In our discussion, we focus on important model aspects, and we investigate some prominent algorithms appearing in the literature in more detail than it was done in previous works.
Michael Breuß, Ashkan Mansouri Yarahmadi
Chapter 3. RGBD-Fusion: Depth Refinement for Diffuse and Specular Objects
Abstract
The popularity of low-cost RGB-D scanners is increasing on a daily basis and has set off a major boost in 3D computer vision research. Nevertheless, commodity scanners often cannot capture subtle details in the environment. In other words, the precision of existing depth scanners is often not accurate enough to recover fine details of scanned objects. In this chapter, we review recent axiomatic methods to enhance the depth map by fusing the intensity and depth information to create detailed range profiles. We present a novel shape-from-shading framework that enhances the quality of recovery of diffuse and specular objects’ depth profiles. The first shading-based depth refinement method we review is designed to work well with Lambertian objects, however, it breaks down in the presence of specularities. To that end, we propose a second method, which utilizes the properties of the built-in monochromatic IR projector and the acquired IR images of common RGB-D scanners and propose a lighting model that accounts for the specular regions in the input image. In the methods suggested above, the detailed geometry is calculated without the need to explicitly find and integrate surface normals, this allows the numerical implementations to work in real-time. Finally, we also show how we can leverage deep learning to refine depth details. We present a neural network that is trained with the above models and can be naturally integrated as part of a larger network architecture. Both quantitative tests and visual evaluations prove that the suggested methods produce state-of-the-art depth reconstruction results.
Roy Or-El, Elad Richardson, Matan Sela, Rom Hershkovitz, Aaron Wetzler, Guy Rosman, Alfred M. Bruckstein, Ron Kimmel
Chapter 4. Non-Rigid Structure-from-Motion and Shading
Abstract
We show how photometric and motion-based approaches can be combined to reconstruct the 3D shape of deformable objects from monocular images. We start by motivating the problem using real-world applications. We give a comprehensive overview of the state-of-the-art approaches and discuss their limitations for practical use in these applications. We then introduce the problem of Non-Rigid Structure-from-Motion and Shading (NRSfMS), where photometric and geometric information is used for reconstruction, without prior knowledge about the shape of the deformable object. We present in detail the first technical solution to NRSfMS and close the chapter with the main remaining open problems.
Mathias Gallardo, Toby Collins, Adrien Bartoli
Chapter 5. On the Well-Posedness of Uncalibrated Photometric Stereo Under General Lighting
Abstract
Uncalibrated photometric stereo aims at estimating the 3D-shape of a surface, given a set of images captured from the same viewing angle, but under unknown, varying illumination. While the theoretical foundations of this inverse problem under directional lighting are well-established, there is a lack of mathematical evidence for the uniqueness of a solution under general lighting. On the other hand, stable and accurate heuristical solutions of uncalibrated photometric stereo under such general lighting have recently been proposed. The quality of the results demonstrated therein tends to indicate that the problem may actually be well-posed, but this still has to be established. The present paper addresses this theoretical issue, considering first-order spherical harmonics approximation of general lighting. Two important theoretical results are established. First, the orthographic integrability constraint ensures uniqueness of a solution up to a global concave–convex ambiguity, which had already been conjectured, yet not proven. Second, the perspective integrability constraint makes the problem well-posed, which generalizes a previous result limited to directional lighting. Eventually, a closed-form expression for the unique least-squares solution of the problem under perspective projection is provided, allowing numerical simulations on synthetic data to empirically validate our findings.
Mohammed Brahimi, Yvain Quéau, Bjoern Haefner, Daniel Cremers
Chapter 6. Recent Progress in Shape from Polarization
Abstract
Photometric cues play an important role in recovering per-pixel 3D information from images. Shape from shading and photometric stereo are popular photometric 3D reconstruction approaches, which rely on inversely analyzing an image formation model of the surface normal, reflectance, and lighting. Similarly, shape from polarization explores radiance variation under different polarizer angles to estimate the surface normal, which does not require an active light source and has less restricted assumptions on reflectance and lighting. This chapter reviews basic principles of shape from polarization and its image formation model for surfaces of different reflection properties. We then survey recent progress in shape from polarization combined with different auxiliary information such as geometric cues, spectral cues, photometric cues, and deep learning, and further introduce how polarization imaging benefits other vision tasks in addition to shape recovery.
Boxin Shi, Jinfa Yang, Jinwei Chen, Ruihua Zhang, Rui Chen
Chapter 7. Estimating Facial Aging Using Light Scattering Photometry
Abstract
Facial aging is a complex process, and the changes in the inner layers of the skin will affect how the light scatters from the skin. To observe whether a light scattering model parameter is suitable to be used for age classification/estimation, this study investigated and analyzed the relationship between the parameter of an analytical-based light scattering model and skins of various ages using photometry method. Multiple models are used to investigate and compare the relationship between the model parameters and the subject’s age. The results show that all of the models’ roughness parameter representation has a significant positive correlation with age (\(p<0.05\)), making it a suitable choice to be made as a feature for estimating/classifying age. This study proves that the parameter(s) for an analytical-based light scattering model can be used as an alternative method for estimating/classifying a person’s age, provided that we know the light incidence and reflectance angles. In the future, this method can be used to work with other age extractors/estimators/classifiers, for the purpose of designing a more robust age estimation/classification method.
Hadi A. Dahlan, Edwin R. Hancock
Backmatter
Metadaten
Titel
Advances in Photometric 3D-Reconstruction
herausgegeben von
Assoc. Prof. Jean-Denis Durou
Prof. Maurizio Falcone
Dr. Yvain Quéau
Dr. Silvia Tozza
Copyright-Jahr
2020
Electronic ISBN
978-3-030-51866-0
Print ISBN
978-3-030-51865-3
DOI
https://doi.org/10.1007/978-3-030-51866-0