Posing 3D Models from Drawing.

Gouvatsos, A., Xiao, Z., Marsden, N. and Zhang, J. J., 2015. Posing 3D Models from Drawing. ACM Computers in Entertainment. (In Press)

Full text available as:

[img]
Preview
PDF (PRE PEER REVIEW VERSION)
Posing 3D models from drawing.pdf - Submitted Version

2MB

Abstract

Inferring the 3D pose of a character from a drawing is a complex and under-constrained problem. Solving it may help automate various parts of an animation production pipeline such as pre-visualisation. In this paper, a novel way of inferring the 3D pose from a monocular 2D sketch is proposed. The proposed method does not make any external assumptions about the model, allowing it to be used on different types of characters. The inference of the 3D pose is formulated as an optimisation problem and a parallel variation of the Particle Swarm Optimisation algorithm called PARAC-LOAPSO is utilised for searching the minimum. Testing in isolation as well as part of a larger scene, the presented method is evaluated by posing a lamp, a horse and a human character. The results show that this method is robust, highly scalable and is able to be extended to various types of models.

Item Type:Article
ISSN:1544-3574
Subjects:UNSPECIFIED
Group:Media School
ID Code:21668
Deposited By: Unnamed user with email symplectic@symplectic
Deposited On:28 Jan 2015 12:58
Last Modified:06 Jan 2016 16:32

Downloads

Downloads per month over past year

More statistics for this item...
Repository Staff Only -