Learning a Style Space for Interactive Line Drawing Synthesis from Animated 3D Models
| dc.contributor.author | Wang, Zeyu | en_US |
| dc.contributor.author | Wang, Tuanfeng Y. | en_US |
| dc.contributor.author | Dorsey, Julie | en_US |
| dc.contributor.editor | Yang, Yin | en_US |
| dc.contributor.editor | Parakkat, Amal D. | en_US |
| dc.contributor.editor | Deng, Bailin | en_US |
| dc.contributor.editor | Noh, Seung-Tak | en_US |
| dc.date.accessioned | 2022-10-04T06:37:52Z | |
| dc.date.available | 2022-10-04T06:37:52Z | |
| dc.date.issued | 2022 | |
| dc.description.abstract | Most non-photorealistic rendering (NPR) methods for line drawing synthesis operate on a static shape. They are not tailored to process animated 3D models due to extensive per-frame parameter tuning needed to achieve the intended look and natural transition. This paper introduces a framework for interactive line drawing synthesis from animated 3D models based on a learned style space for drawing representation and interpolation. We refer to style as the relationship between stroke placement in a line drawing and its corresponding geometric properties. Starting from a given sequence of an animated 3D character, a user creates drawings for a set of keyframes. Our system embeds the raster drawings into a latent style space after they are disentangled from the underlying geometry. By traversing the latent space, our system enables a smooth transition between the input keyframes. The user may also edit, add, or remove the keyframes interactively, similar to a typical keyframe-based workflow. We implement our system with deep neural networks trained on synthetic line drawings produced by a combination of NPR methods. Our drawing-specific supervision and optimization-based embedding mechanism allow generalization from NPR line drawings to user-created drawings during run time. Experiments show that our approach generates high-quality line drawing animations while allowing interactive control of the drawing style across frames. | en_US |
| dc.description.sectionheaders | Sketch and Modeling | |
| dc.description.seriesinformation | Pacific Graphics Short Papers, Posters, and Work-in-Progress Papers | |
| dc.identifier.doi | 10.2312/pg.20221237 | |
| dc.identifier.isbn | 978-3-03868-190-8 | |
| dc.identifier.pages | 1-6 | |
| dc.identifier.pages | 6 pages | |
| dc.identifier.uri | https://doi.org/10.2312/pg.20221237 | |
| dc.identifier.uri | https://diglib.eg.org:443/handle/10.2312/pg20221237 | |
| dc.publisher | The Eurographics Association | en_US |
| dc.rights | Attribution 4.0 International License | |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
| dc.subject | CCS Concepts: Computing methodologies → Non-photorealistic rendering; Animation; Learning latent representations | |
| dc.subject | Computing methodologies → Non photorealistic rendering | |
| dc.subject | Animation | |
| dc.subject | Learning latent representations | |
| dc.title | Learning a Style Space for Interactive Line Drawing Synthesis from Animated 3D Models | en_US |