Variational harmonic maps for space deformation

Ben‐Chen, Mirela; Weber, Ofir; Gotsman, Craig

doi:10.1145/1576246.1531340

Cited by 64 publications

(93 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this context, we note that many specific mesh-based optimization techniques have been developed for a range of applications, including image and video retargeting [14], [15] and detail-preserving shape manipulation and deformation [16], [17], [18], [19].…”

Section: Related Workmentioning

confidence: 99%

Fisheye Video Correction

Jin

et al. 2012

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Abstract-Various types of video can be captured with fisheye lenses; their wide field of view is particularly suited to surveillance video. However, fisheye lenses introduce distortion, and this changes as objects in the scene move, making fisheye video difficult to interpret. Current still fisheye image correction methods are either limited to small angles of view, or are strongly content dependent, and therefore unsuitable for processing video streams. We present an efficient and robust scheme for fisheye video correction, which minimizes time-varying distortion and preserves salient content in a coherent manner. Our optimization process is controlled by user annotation, and takes into account a wide set of measures addressing different aspects of natural scene appearance. Each is represented as a quadratic term in an energy minimization problem, leading to a closed-form solution via a sparse linear system. We illustrate our method with a range of examples, demonstrating coherent natural-looking video output. The visual quality of individual frames is comparable to those produced by state-of-the-art methods for fisheye still photograph correction.

show abstract

Section: Related Workmentioning

confidence: 99%

Fisheye Video Correction

Jin

et al. 2012

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

show abstract

“…However, it lacks an underlying structure to intuitively generate and deform it in a volume and shapepreserving way. Works such as [1] allow the user to interact with the cage using a small number of position and orientation constraints. However, how to generate the cage remains an issue.…”

Section: Deformation Modelmentioning

confidence: 99%

Cage-Based Motion Recovery Using Manifold Learning

Duveau

Courtemanche

Revéret

et al. 2012

2012 Second International Conference on 3D Imaging, Modeling, Processing, Visualization &Amp; Transmission

View full text Add to dashboard Cite

We present a flexible model-based approach for the recovery of parameterized motion from a sequence of 3D meshes without temporal coherence. Unlike previous model-based approaches using skeletons, we embed the deformation of a reference mesh template within a low polygonal representation of the mesh, namely the cage, using Green Coordinates. The advantage is a less constrained model that more robustly adapts to noisy observations while still providing structured motion information, as required by several applications. The cage is parameterized with a set of 3D features dedicated to the description of human morphology. This allows to formalize a novel representation of 3D meshed and articulated characters, the Oriented Quads Rigging (OQR). To regularize the tracking, the OQR space is subsequently constrained to plausible poses using manifold learning. Results are shown for sequences of meshes, with and without temporal coherence, obtained from multiple view videos preprocessed by visual hull. Motion recovery applications are illustrated with a motion transfer encoding and the extraction of trajectories of anatomical joints. Validation is performed on the HumanEva II database.

show abstract

“…Recently, cage-based methods have been proposed which embed the target object within an arbitrary non-convex polyhedral cage, and then generate a spatial deformation based on deformations of the cage [14,13,15,3]. The cage is a closed surface and typically a coarse mesh of the target object is used.…”

Section: Related Workmentioning

confidence: 99%

WarpCurves: A tool for explicit manipulation of implicit surfaces

Sugihara

Wyvill

Schmidt

2010

Computers & Graphics

View full text Add to dashboard Cite

We introduce WarpCurves, a technique for interactively manipulating an implicit surface using curve-based spatial deformations. Although implicit surfaces have several advantages in 3D modeling, current workflows are limited by the compositional nature of implicit modeling. Wide classes of surface features that are easy to create with the direct manipulation tools available for explicit surface representations are difficult to reproduce using volumetric implicit operations. We describe a novel spatial deformation that can be used to approximate direct surface manipulation. With our method an artist first draws a curve on the current surface to indicate the feature region-of-interest. Deformations applied to this handle curve are transferred to the implicit surface via an automatically-constructed C 2 continuous space mapping. Additional curves can be added in a hierarchical manner to create complex shapes. Our technique is implemented as a node in the BlobTree hierarchical implicit volume representation, and hence can be used along with other volumetric nodes (operators) such as blending and CSG. Our results show that surface deformations which would be difficult to reproduce using existing volumetric operations can be quickly constructed using warp curves, making them a valuable addition to the implicit modeling toolbox.

show abstract

Variational harmonic maps for space deformation

Cited by 64 publications

References 23 publications

Fisheye Video Correction

Fisheye Video Correction

Cage-Based Motion Recovery Using Manifold Learning

WarpCurves: A tool for explicit manipulation of implicit surfaces

Contact Info

Product

Resources

About