SCA 03: Eurographics/SIGGRAPH Symposium on Computer Animation
https://diglib.eg.org:443/handle/10.2312/433
ISBN 1-58113-659-52024-03-28T12:48:17ZSound-by-Numbers: Motion-Driven Sound Synthesis
https://diglib.eg.org:443/handle/10.2312/SCA.SCA03.349-356
Sound-by-Numbers: Motion-Driven Sound Synthesis
Cardle, M.; Brooks, S.; Bar-Joseph, Z.; Robinson, P.
D. Breen and M. Lin
We present the first algorithm for automatically generating soundtracks for input animation based on other animations' soundtrack. This technique can greatly simplify the production of soundtracks in computer animation and video by re-targeting existing soundtracks. A segment of source audio is used to train a statistical model which is then used to generate variants of the original audio to fit particular constraints. These constraints can either be specified explicitly by the user in the form of large-scale properties of the sound texture, or determined automatically and semi-automatically by matching similar motion events in a source animation to those in the target animation.
2003-01-01T00:00:00ZFootSee: an Interactive Animation System
https://diglib.eg.org:443/handle/10.2312/SCA.SCA03.329-338
FootSee: an Interactive Animation System
Yin, KangKang; Pai, Dinesh K.
D. Breen and M. Lin
We present an intuitive animation interface that uses a foot pressure sensor pad to interactively control avatars for video games, virtual reality, and low-cost performance-driven animation. During an offline training phase, we capture full body motions with a motion capture system, as well as the corresponding foot-ground pressure distributions with a pressure sensor pad, into a database. At run time, the user acts out the animation desired on the pressure sensor pad. The system then tries to see the motion only through the foot-ground interactions measured, and the most appropriate motions from the database are selected, and edited online to drive the avatar.We describe our motion recognition, motion blending, and inverse kinematics algorithms in detail. They are easy to implement, and cheap to compute. FootSee can control a virtual avatar in a fixed latency of 1 second with reasonable accuracy. Our system thus makes it possible to create interactive animations without the cost or inconveniences of a full body motion capture system.
2003-01-01T00:00:00ZStylizing Motion with Drawings
https://diglib.eg.org:443/handle/10.2312/SCA.SCA03.309-319
Stylizing Motion with Drawings
Li, Yin; Gleicher, Michael; Xu, Ying-Qing; Shum, Heung-Yeung
D. Breen and M. Lin
In this paper, we provide a method that injects the expressive shape deformations common in traditional 2D animation into an otherwise rigid 3D motion captured animation. We allow a traditional animator to modify frames in the rendered animation by redrawing the key features such as silhouette curves. These changes are then integrated into the animation. To perform this integration, we divide the changes into those that can be made by altering the skeletal animation, and those that must be made by altering the character's mesh geometry. To propagate mesh changes into other frames, we introduce a new image warping technique that takes into account the character's 3D structure. The resulting technique provides a system where an animator can inject stylization into 3D animation.
2003-01-01T00:00:00ZA Sketching Interface for Articulated Figure Animation
https://diglib.eg.org:443/handle/10.2312/SCA.SCA03.320-328
A Sketching Interface for Articulated Figure Animation
Davis, James; Agrawala, Maneesh; Chuang, Erika; Popovic, Zoran; Salesin, David
D. Breen and M. Lin
We introduce a new interface for rapidly creating 3D articulated figure animation, from 2D sketches of the character in the desired key frame poses. Since the exact 3D animation corresponding to a set of 2D drawings is ambiguous we first reconstruct the possible 3D configurations and then apply a set of constraints and assumptions to present the user with the most likely 3D pose. The user can refine this candidate pose by choosing among alternate poses proposed by the system. This interface is supported by pose reconstruction and optimization methods specifically designed to work with imprecise hand drawn figures. Our system provides a simple, intuitive and fast interface for creating rough animations that leverages our users existing ability to draw. The resulting key framed sequence can be exported to commercial animation packages for interpolation and additional refinement.
2003-01-01T00:00:00Z