Direct Estimation of Non-Rigid Registrations with Image-Based Self-Occlusion Reasoning

Gripon, Vincent; Bartoli, Adrien; Sayd, Patrick

doi:10.1109/iccv.2007.4408989

Cited by 16 publications

(15 citation statements)

References 30 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As far as 2D problems are concerned, their more recent incarnations have proved effective for image registration [13,14] and non-rigid surface detection [15,16]. Many variations of these models have also been proposed to address 3D problems, including superquadrics [1], triangulated surfaces [2], or thin-plate splines [17].…”

Section: Related Workmentioning

confidence: 99%

Closed-Form Solution to Non-rigid 3D Surface Registration

Salzmann

Moreno-Noguer

Lepetit

et al. 2008

Lecture Notes in Computer Science

137

View full text Add to dashboard Cite

Abstract. We present a closed-form solution to the problem of recovering the 3D shape of a non-rigid inelastic surface from 3D-to-2D correspondences. This lets us detect and reconstruct such a surface by matching individual images against a reference configuration, which is in contrast to all existing approaches that require initial shape estimates and track deformations from image to image. We represent the surface as a mesh, and write the constraints provided by the correspondences as a linear system whose solution we express as a weighted sum of eigenvectors. Obtaining the weights then amounts to solving a set of quadratic equations accounting for inextensibility constraints between neighboring mesh vertices. Since available closed-form solutions to quadratic systems fail when there are too many variables, we reduce the number of unknowns by expressing the deformations as a linear combination of modes. The overall closed-form solution then becomes tractable even for complex deformations that require many modes.

show abstract

Section: Related Workmentioning

confidence: 99%

Closed-Form Solution to Non-rigid 3D Surface Registration

Salzmann

Moreno-Noguer

Lepetit

et al. 2008

Lecture Notes in Computer Science

137

View full text Add to dashboard Cite

show abstract

“…Other researchers [14,7,17] also proposed to find deformations of an object in a sequence of acquired images. These methods generally consist of estimation of the parameters of the warping function that registers the reference image, in which the object is mainly planar, to the input image where the object is deformed.…”

Section: Related Workmentioning

confidence: 99%

“…These methods generally consist of estimation of the parameters of the warping function that registers the reference image, in which the object is mainly planar, to the input image where the object is deformed. Pilet et al [14] and Gay-Bellile et al [7] relied on feature points. While the former can deal with a huge amount of outliers, the latter is relatively sensitive to them.…”

Section: Related Workmentioning

confidence: 99%

Simultaneous Reconstruction and Tracking of Non-planar Templates

Lieberknecht¹,

Benhimane²,

Ilić

2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In this paper, we address the problem of simultaneous tracking and reconstruction of non-planar templates in real-time. Classical approaches to template tracking assume planarity and do not attempt to recover the shape of an object. Structure from motion approaches use feature points to recover camera pose and reconstruct the scene from those features, but do not produce dense 3D surface models. Finally, deformable surface tracking approaches assume a static camera and impose strong deformation priors to recover dense 3D shapes. The proposed method simultaneously recovers the camera motion and deforms the template such that an approximation of the underlying 3D structure is recovered. Spatial smoothing is not explicitly imposed, thus templates of smooth and non-smooth objects can be equally handled. The problem is formalized as an energy minimization based on image intensity differences. Quantitative and qualitative evaluation on both real and synthetic data is presented, we compare the proposed approach to related methods and demonstrate that the recovered camera pose is close to the ground truth even in presence of strong blur and low texture.

show abstract

“…Generally, image-based methods yield more accurate results in non-rigid deformation estimation than feature-based techniques because they exploit the entire image instead of distinct points. In [8] Gay-Belille et al proposed a direct method to estimate deformable motion under self-occlusions. External occlusions are only considered in a robust estimator which rejects outliers based on image intensity differences.…”

Section: Introduction and Related Workmentioning

confidence: 99%

“…In recent years, also the issue of retexturing the tracked surface was addressed. Current retexturing methods of deformable surfaces in single-view video usually either do not account for shading and illumination at all [8] or treat geometric and photometric parameter estimation separately [9,10]. Some approaches that require markers for tracking use inpainting techniques to establish a shading map [11,9].…”

Section: Introduction and Related Workmentioning

confidence: 99%

Realistic cloth augmentation in single view video under occlusions

Hilsmann

Schneider

Eisert

2010

Computers & Graphics

View full text Add to dashboard Cite

Augmenting cloth in real video is a challenging task because cloth performs complex motions and deformations and produces complex shading on the surface. Therefore, for a realistic augmentation of cloth, parameters describing both deformation as well as shading properties are needed. Furthermore, objects occluding the real surface have to be taken into account as on the one hand they affect the parameter estimation and on the other hand should also occlude the virtually textured surface. This is especially challenging in monocular image sequences where a 3-dimensional reconstruction of complex surfaces is difficult to achieve. In this paper, we present a method for cloth retexturing in monocular image sequences under external occlusions without a reconstruction of the 3-dimensional geometry. We exploit direct image information and simultaneously estimate deformation and photometric parameters using a robust estimator which detects occluded pixels as outliers. Additionally, we exploit the estimated parameters to establish an occlusion map from local statistical color models of texture surface patches that are established during tracking. With this information we can produce convincing augmented results.

show abstract

Direct Estimation of Non-Rigid Registrations with Image-Based Self-Occlusion Reasoning

Cited by 16 publications

References 30 publications

Closed-Form Solution to Non-rigid 3D Surface Registration

Closed-Form Solution to Non-rigid 3D Surface Registration

Simultaneous Reconstruction and Tracking of Non-planar Templates

Realistic cloth augmentation in single view video under occlusions

Contact Info

Product

Resources

About