Material-Aware Mesh Deformations

109

Recent shape editing techniques, especially for man-made models, have gradually shifted focus from maintaining local, low-level geometric features to preserving structural, high-level characteristics like symmetry and parallelism. Such new editing goals typically require a pre-processing shape analysis step to enable subsequent shape editing. Observing that most editing of shapes involves manipulating their constituent components, we introduce component-wise controllers that are adapted to the component characteristics inferred from shape analysis. The controllers capture the natural degrees of freedom of individual components and thus provide an intuitive user interface for editing. A typical model usually results in a moderate number of controllers, allowing easy establishment of semantic relations among them by automatic shape analysis supplemented with user interaction. We propose a component-wise propagation algorithm to automatically preserve the established inter-relations while maintaining the defining characteristics of individual controllers and respecting the user-specified modeling constraints. We extend these ideas to a hierarchical setup, allowing the user to adjust the tool complexity with respect to the desired modeling complexity. We demonstrate the effectiveness of our technique on a wide range of manmade models with structural features, often containing multiple connected pieces.

Section: Related Workmentioning

confidence: 99%

Component‐wise Controllers for Structure‐Preserving Shape Manipulation

Zheng

Cohen–Or

et al. 2011

109

“…Many works assume a prior is provided by users or artists in the form of kinematic skeletons [GWBB09,AB15,TSR * 14a,BTG * 12, YY14,TSR * 14b] or painted stiffness [PJS06]. Many works assume a prior is provided by users or artists in the form of kinematic skeletons [GWBB09,AB15,TSR * 14a,BTG * 12, YY14,TSR * 14b] or painted stiffness [PJS06].…”

Section: Related Workmentioning

confidence: 99%

“…Many works assume a prior is provided by users or artists in the form of kinematic skeletons [GWBB09,AB15,TSR * 14a,BTG * 12, YY14,TSR * 14b] or painted stiffness [PJS06]. Popa et al [PJS06] learn the material stiffness of animal meshes by analyzing a set of vertex-aligned 3D meshes in various poses. Anguelov et al [AKP * 04] use a set of registered 3D range scans of human bodies in a variety of configurations to construct skeletons using graphical models.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Learning 3D Deformation of Animals from 2D Images

Kanazawa

Kovalsky

Jacobs

2016

Understanding how an animal can deform and articulate is essential for a realistic modification of its 3D model. In this paper, we show that such information can be learned from user-clicked 2D images and a template 3D model of the target animal. We present a volumetric deformation framework that produces a set of new 3D models by deforming a template 3D model according to a set of user-clicked images. Our framework is based on a novel locally-bounded deformation energy, where every local region has its own stiffness value that bounds how much distortion is allowed at that location. We jointly learn the local stiffness bounds as we deform the template 3D mesh to match each user-clicked image. We show that this seemingly complex task can be solved as a sequence of convex optimization problems. We demonstrate the effectiveness of our approach on cats and horses, which are highly deformable and articulated animals. Our framework produces new 3D models of animals that are significantly more plausible than methods without learned stiffness.

“…In this paper we adapt the discrete shell energy [GHDS03] for our mesh deformation operator. Thanks to this non‐linear, physics‐based energy our deformations are free of linearization artefacts, and we can control the local surface stiffness (similar to [PJS06, HZS*06, KG08]) as well as the relation of stretching and bending resistance. Note that while PriMo [BPGK06] performs equally well for pure deformation, it cannot be easily combined with mesh interpolation.…”

Section: Related Workmentioning

confidence: 99%

Example‐Driven Deformations Based on Discrete Shells

Fröhlich

Botsch

2011

162

Despite the huge progress made in interactive physics‐based mesh deformation, manipulating a geometrically complex mesh or posing a detailed character is still a tedious and time‐consuming task. Example‐driven methods significantly simplify the modelling process by incorporating structural or anatomical knowledge learned from example poses. However, these approaches yield counter‐intuitive, non‐physical results as soon as the shape space spanned by the example poses is left. In this paper, we propose a modelling framework that is both example‐driven and physics‐based and thereby overcomes the limitations of both approaches. Based on an extension of the discrete shell energy we derive mesh deformation and mesh interpolation techniques that can be seamlessly combined into a simple and flexible mesh‐based inverse kinematics system.