Text-to-Vector Generation with Neural Path Representation
ACM Transactions on Graphics · 19.07.2024 · 43 (4) · 1-13
DOI: 10.1145/3658204 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 19.07.2024. Verfasst von Peiying Zhang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: Hong Kong Research Grants Council (RGC) General Research Fund.
Abstract (Originalsprache)
Vector graphics are widely used in digital art and highly favored by designers due to their scalability and layer-wise properties. However, the process of creating and editing vector graphics requires creativity and design expertise, making it a time-consuming task. Recent advancements in text-to-vector (T2V) generation have aimed to make this process more accessible. However, existing T2V methods directly optimize control points of vector graphics paths, often resulting in intersecting or jagged paths due to the lack of geometry constraints. To overcome these limitations, we propose a novel neural path representation by designing a dual-branch Variational Autoencoder (VAE) that learns the path latent space from both sequence and image modalities. By optimizing the combination of neural paths, we can incorporate geometric constraints while preserving expressivity in generated SVGs. Furthermore, we introduce a two-stage path optimization method to improve the visual and topological quality of generated SVGs. In the first stage, a pre-trained text-to-image diffusion model guides the initial generation of complex vector graphics through the Variational Score Distillation (VSD) process. In the second stage, we refine the graphics using a layer-wise image vectorization strategy to achieve clearer elements and structure. We demonstrate the effectiveness of our method through extensive experiments and showcase various applications. The project page is https://intchous.github.io/T2V-NPR.
Förderung
- Hong Kong Research Grants Council (RGC) General Research Fund
Zitieren
APA
Zhang, P., Zhao, N., & Liao, J. (2024). Text-to-Vector Generation with Neural Path Representation. ACM Transactions on Graphics, 43(4), 1-13. https://doi.org/10.1145/3658204
Vancouver
Zhang P, Zhao N, Liao J. Text-to-Vector Generation with Neural Path Representation. ACM Transactions on Graphics. 2024;43(4):1-13. doi:10.1145/3658204
BibTeX
@article{Zhang2024,
author = {Zhang, Peiying and Zhao, Nanxuan and Liao, Jing},
title = {Text-to-Vector Generation with Neural Path Representation},
journal = {ACM Transactions on Graphics},
year = {2024},
volume = {43},
number = {4},
pages = {1--13},
doi = {10.1145/3658204}
}
EUVIMED