PG2014short

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/7750

Browse

Browsing PG2014short by Subject "Animation"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Automatic 3D Posing from 2D Hand-Drawn Sketches
    (The Eurographics Association, 2014) Gouvatsos, Alexandros; Xiao, Zhidong; Marsden, Neil; Zhang, Jian J.; John Keyser and Young J. Kim and Peter Wonka
    Inferring 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.
  • Thumbnail Image
    Item
    Data-Driven Fire Synthesis and Design
    (The Eurographics Association, 2014) Wong, Sai-Keung; Chang, Tse-Ching; Ho, Tan-Chi; Chuang, Jung-Hong; John Keyser and Young J. Kim and Peter Wonka
    We present a data-driven synthesis approach to design and animate fires in desired shapes and motions. At the preprocessing stage, our system simulates a set of basis fires under specific simulation configurations and stores these basis fires as pathlines in a database. At the design stage, a user sketches a sequence of curves to design the desired shapes of target fires. Then, we compute a subset of basis fires to fit the curves. After that the target fires are synthesized by combining the basis fires. As our method generates target fires along the user sketched curves, our approach enables users to design the fire shapes in an intuitive manner. Experimental results show that our approach can synthesize fires in desired shapes and motions.