From 3D shape capture of animated models

Hilton, Adrian; Starck, Jonathan; Collins, Gordon

doi:10.1109/tdpvt.2002.1024069

Cited by 21 publications

(11 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The soles of the feet, for example, will be filled in flat. A related displacement-mapped approach was also developed in [1]. But a pre-condition for avoiding the crossing of sample rays is that the template surface is already a fairly close match to the original [1].…”

Section: Related Workmentioning

confidence: 99%

Analysis of segmented human body scans

Lee

Shu

2007

Proceedings of Graphics Interface 2007 on - GI '07

View full text Add to dashboard Cite

Analysis on a dataset of 3D scanned surfaces have presented problems because of incompleteness on the surfaces and because of variances in shape, size and pose. In this paper, a high-resolution generic model is aligned to data in the Civilian American and European Surface Anthropometry Resources (CAESAR) database in order to obtain a consistent parameterization. A Radial Basis Function (RBF) network is built for rough deformation by using landmark information from the generic model, anatomical landmarks provided by CAESAR dataset and virtual landmarks created automatically for geometric deformation. Fine mapping then successfully applies a weighted sum of errors on both surface data and the smoothness of deformation. Compared with previous methods, our approach makes robust alignment in a higher efficiency. This consistent parameterization also makes it possible for Principal Components Analysis (PCA) on the whole body as well as human body segments. Our analysis on segmented bodies displays a richer variation than that of the whole body. This analysis indicates that a wider application of human body reconstruction with segments is possible in computer animation.

show abstract

Section: Related Workmentioning

confidence: 99%

Analysis of segmented human body scans

Lee

Shu

2007

Proceedings of Graphics Interface 2007 on - GI '07

View full text Add to dashboard Cite

show abstract

“…Surface completion An important contribution of this paper is the projection method described in 3 that is used to map a texture signal from a proxy surface onto an inconsistent mesh. Conceptually similar, many surface completion methods [2,19,1,28,18,14] establish a map between an incomplete mesh and a template surface to fill holes or missing parts in a surface. Except for [14], all these methods need a set of correspondences between feature points on both surfaces.…”

Section: Previous Workmentioning

confidence: 99%

“…Conceptually similar, many surface completion methods [2,19,1,28,18,14] establish a map between an incomplete mesh and a template surface to fill holes or missing parts in a surface. Except for [14], all these methods need a set of correspondences between feature points on both surfaces. In particular, if the inconsistent mesh consists of many disconnected components (as it can be often observed in meshes triangulated from NURBS) the number of required correspondences and thus the amount of necessary user interaction is very high.…”

Section: Previous Workmentioning

confidence: 99%

Texture Atlas Generation for Inconsistent Meshes and Point Sets

Degener

Klein

2007

IEEE International Conference on Shape Modeling and Applications 2007 (SMI '07)

View full text Add to dashboard Cite

In order to compute texture atlases with low stretch and hardly visible texture seams existing texture mapping tools pose high demands on the quality of surface representations like consistent orientation, watertightness, or manifoldness which many models commonly used in day-to-day modeling practice fail to meet. In this paper we propose an approach that bridges the gap between requirements of high quality texture mapping tools and poor mesh connectivity of models used in practice. In the spirit of classical two-part mapping an intermediate proxy surface is created that can be processed by high quality texture mapping tools. The texture signal is transfered to the original geometry using a novel mapping technique.Avoiding a modification of the original geometry typical problems of mesh repairing approaches like approximation errors or feature corruption are circumvented. As our method poses almost no demands on connectivity it can also be applied to point clouds. Contrary to classical twopart mapping, the method requires little user-interaction.Its robustness and quality are demonstrated in several examples.

show abstract

“…We term this detail representation 3D skin. We utilize point-to-surface mapping 20,21 to construct the detail representation. Point-to-surface mapping enables a point in 3D space to be mapped to a surface using 3D ray-casting projection based on interpolated surface normals.…”

Section: D Skin Constructionmentioning

confidence: 99%

Facial shape and 3D skin

Lee

Soon²

2006

Computer Animation & Virtual

View full text Add to dashboard Cite

We present novel ideas for facial shape and skin simulation on extremely detailed threedimensional facial meshes. Our input database is composed of a small number of scanned human faces with resolutions up to several million triangles, where even the pores are clearly distinguished. We show how to decompose the facial meshes into the global shape of the face plus skin detail (3D skin), and then to reconstitute them. Our modeling methodology allows us to simulate the exaggeration of the facial global shape, retaining the original skin detail, as well as to transfer 3D skin from one face to another. First, we represent all the input faces in terms of a homogeneous structure on the base model in low resolution by using mesh adaptation techniques. Second, the differences between the original mesh and a base mesh, which appear as skin detail, are captured and stored, so that each face is decomposed into the global shape (a base mesh) plus skin detail. Face reconstitution after global shape exaggeration and/or skin transfer enables delicate simulation of facial models. In addition, we can increase the resolution of any model scanned at a low resolution by transferring skin from a higher resolution model. Our method shows successful manipulation of the minute structure of 3D skin differently from other methods such as Normal Mapping, Displacement Mapping, Displaced Subdivision Surfaces, and Normal Meshes where none of these techniques show manipulation of minute structure like ours and only approximation is used while our method recovers the original structure.

show abstract

From 3D shape capture of animated models

Cited by 21 publications

References 17 publications

Analysis of segmented human body scans

Analysis of segmented human body scans

Texture Atlas Generation for Inconsistent Meshes and Point Sets

Facial shape and 3D skin

Contact Info

Product

Resources

About