Monocular deformable 3D reconstruction is the general problem of recovering the 3D shape of a deformable object from monocular 2D images. Several scenarios have emerged: the Shape-from-Template (SfT) and the Non-Rigid Structure-from-Motion (NRSfM) are two approaches intensively studied for their practicability. The former uses a single image depicting the deforming object and a template (a textured 3D shape of this object in a reference pose). The latter does not use a template, but uses several images and recovers the 3D shape in each image. Both approaches rely on the motion of correspondences between the images and deformation priors, which restrict their use to well-textured surfaces which deform smoothly. This thesis advances the state-of-the-art in SfT and NRSfM in two main directions. The first direction is to study SfT for the case of 1D templates (i.e. curved, thin structures such as ropes and cables). The second direction is to develop algorithms in SfT and NRSfM that exploit multiple visual cues and can solve complex, real-world cases which were previously unsolved. We focus on isometric deformations and reconstruct the outer part of the object. The technical and scientific contributions of this thesis are divided into four parts. The first part of this thesis studies the case of a curvilinear template embedded in 2D or 3D space, referred to Curve SfT. We propose a thorough theoretical analysis and practical solutions for Curve SfT. Despite its apparent simplicity, Curve SfT appears to be a complex problem: it cannot be solved locally using exact non-holonomic partial differential equation and is only solvable up to a finite number of ambiguous solutions. A major technical contribution is a computational solution based on our theory, which generates all the ambiguous solutions.The second part of this thesis deals with a limitation of SfT methods: reconstructing creases. This is due to the sparsity of the motion constraint and regularization. We propose two contributions which rely on a non-convex energy minimization framework. First, we complement the motion constraint with a robust boundary contour constraint. Second, we implicitly model creases with a dense mesh-based surface representation and an associated robust smoothing constraint, which deactivates curvature smoothing automatically where needed, without knowing a priori the crease location. The third part of this thesis is dedicated to another limitation of SfT: reconstructing poorly-textured surfaces. This is due to correspondences which cannot be obtained so easily on poorly-textured surfaces (either sparse or dense). As shading reveals details on poorly-textured surfaces, we propose to combine shading and SfT. We have two contributions. The first is a cascaded initialization which estimates sequentially the surface's deformation, the scene illumination, the camera response and then the surface albedos from deformed monocular images. The second is to integrate shading to our previous energy minimization framework for simultaneously refining deformation and photometric parameters.The last part of this thesis relaxes the knowledge of the template and addresses two limitations of NRSfM: reconstructing poorly-textured surfaces with creases. Our major contribution is an extension of the second framework to recover jointly the 3D shapes of all input images and the surface albedos without any template.

7. Future directions -- Bibliography -- Authors' biographies.

Vladislav Golyanik proposes several new methods for dense non-rigid structure from motion (NRSfM) as well as alignment of point clouds. The introduced methods improve the state of the art in various aspects, i.e. in the ability to handle inaccurate point tracks and 3D data with contaminations. NRSfM with shape priors obtained on-the-fly from several unoccluded frames of the sequence and the new gravitational class of methods for point set alignment represent the primary contributions of this book. About the Author: Vladislav Golyanik is currently a postdoctoral researcher at the Max Planck Institute for Informatics in Saarbrücken, Germany. The current focus of his research lies on 3D reconstruction and analysis of general deformable scenes, 3D reconstruction of human body and matching problems on point sets and graphs. He is interested in machine learning (both supervised and unsupervised), physics-based methods as well as new hardware and sensors for computer vision and graphics (e.g., quantum computers and event cameras).

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.

This thesis addresses the problem of deformable and articulated structure from motion from monocular uncalibrated video sequences. Structure from motion is defined as the problem of recovering information about the 3D structure of scenes imaged by a camera in a video sequence. Our study aims at the challenging problem of non-rigid shapes (e.g. a beating heart or a smiling face). Non-rigid structures appear constantly in our everyday life, think of a bicep curling, a torso twisting or a smiling face. Our research seeks a general method to perform 3D shape recovery purely from data, without having to rely on a pre-computed model or training data. Open problems in the field are the difficulty of the non-linear estimation, the lack of a real-time system, large amounts of missing data in real-world video sequences, measurement noise and strong deformations. Solving these problems would take us far beyond the current state of the art in non-rigid structure from motion. This dissertation presents our contributions in the field of non-rigid structure from motion, detailing a novel algorithm that enforces the exact metric structure of the problem at each step of the minimisation by projecting the motion matrices onto the correct deformable or articulated metric motion manifolds respectively. An important advantage of this new algorithm is its ability to handle missing data which becomes crucial when dealing with real video sequences. We present a generic bilinear estimation framework, which improves convergence and makes use of the manifold constraints. Finally, we demonstrate a sequential, frame-by-frame estimation algorithm, which provides a 3D model and camera parameters for each video frame, while simultaneously building a model of object deformations.

Abstract: 3D reconstruction of deformable (or non-rigid) scenes from a set of monocular 2D image observations is a long-standing and actively researched area of computer vision and graphics. It is an ill-posed inverse problem, since--without additional prior assumptions--it permits infinitely many solutions leading to accurate projection to the input 2D images. Non-rigid reconstruction is a foundational building block for downstream applications like robotics, AR/VR, or visual content creation. The key advantage of using monocular cameras is their omnipresence and availability to the end users as well as their ease of use compared to more sophisticated camera set-ups such as stereo or multi-view systems. This survey focuses on state-of-the-art methods for dense non-rigid 3D reconstruction of various deformable objects and composite scenes from monocular videos or sets of monocular views. It reviews the fundamentals of 3D reconstruction and deformation modeling from 2D image observations. We then start from general methods--that handle arbitrary scenes and make only a few prior assumptions--and proceed towards techniques making stronger assumptions about the observed objects and types of deformations (e.g. human faces, bodies, hands, and animals). A significant part of this STAR is also devoted to classification and a high-level comparison of the methods, as well as an overview of the datasets for training and evaluation of the discussed techniques. We conclude by discussing open challenges in the field and the social aspects associated with the usage of the reviewed methods