ABSTRACT
The Pando Thrower is a weapon of great importance in Disney’s "Strange World." The explosive Pando fuel mixture is expelled with turbulent, fluid-like motion, with branching arcs of lightning and the electrifying presence of high energy particles. During effects development, previous stylization methods were improved and expanded to enable the combination of distinctly different natural phenomena into a single fantastical effect. In this talk, we present our use of Neural Style Transfer (NST) to reshape volume simulations into lightning-laced electrical reactions.
Supplemental Material
- Leon A. Gatys, Alexander S. Ecker, and Matthias Bethge. 2015. A Neural Algorithm of Artistic Style. arxiv:1508.06576 [cs.CV]Google Scholar
- Byungsoo Kim, Vinicius C. Azevedo, Markus Gross, and Barbara Solenthaler. 2019. Transport-based neural style transfer for smoke simulations. ACM Transactions on Graphics 38, 6 (nov 2019), 1–11. https://doi.org/10.1145/3355089.3356560Google ScholarDigital Library
Index Terms
- Diving Deeper into Volume Style Transfer
Recommendations
Simulating cartoon style animation
NPAR '02: Proceedings of the 2nd international symposium on Non-photorealistic animation and renderingTraditional hand animation is in many cases superior to simulated motion for conveying information about character and events. Much of this superiority comes from an animator's ability to abstract motion and play to human perceptual effects. However, ...
Reimagining Animation Making through Style Transfer
SA '23: SIGGRAPH Asia 2023 Art Papers"Dissolution” and “Cunabula” are experimental animation projects that explore the potential of artistic style transfer with neural networks in animation filmmaking. The objective is to discover novel production methods using fast, arbitrary, and stroke-...
Evolving Neural Style Transfer Blends
Artificial Intelligence in Music, Sound, Art and DesignAbstractNeural style transfer is an image filtering technique used in both digital art practice and commercial software. We investigate blending the styles afforded by neural models via interpolation and overlaying different stylisations. In order to ...
Comments