Automatic 3D Posing from 2D Hand-Drawn Sketches

dc.contributor.authorGouvatsos, Alexandrosen_US
dc.contributor.authorXiao, Zhidongen_US
dc.contributor.authorMarsden, Neilen_US
dc.contributor.authorZhang, Jian J.en_US
dc.contributor.editorJohn Keyser and Young J. Kim and Peter Wonkaen_US
dc.date.accessioned2014-12-16T07:23:39Z
dc.date.available2014-12-16T07:23:39Z
dc.date.issued2014en_US
dc.description.abstractInferring the 3D pose of a character from a drawing is a non-trivial 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 3D pose inference 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 and a horse character. The results show that this method is robust and is able to be extended to various types of models.en_US
dc.description.seriesinformationPacific Graphics Short Papersen_US
dc.identifier.isbn978-3-905674-73-6en_US
dc.identifier.urihttps://doi.org/10.2312/pgs.20141264en_US
dc.publisherThe Eurographics Associationen_US
dc.subjectI.2.8 [Artificial Intelligence]en_US
dc.subjectProblem Solvingen_US
dc.subjectControl Methodsen_US
dc.subjectSearchen_US
dc.subjectHeuristic methodsen_US
dc.subjectI.2.10 [Artificial Intelligence]en_US
dc.subjectVision and Scene Understandingen_US
dc.subjectShapeen_US
dc.subjectI.3.7 [Computer Graphics]en_US
dc.subjectThree Dimensional Graphics and Realismen_US
dc.subjectAnimationen_US
dc.subjectI.4.9 [Image Processing and Computer Vision]en_US
dc.subjectApplicationsen_US
dc.titleAutomatic 3D Posing from 2D Hand-Drawn Sketchesen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
125-130.pdf
Size:
2.11 MB
Format:
Adobe Portable Document Format
Collections