Synthesis and Validation of Virtual Woodcuts Generated with Reaction-Diffusion

Mesquita, Davi Padilha; Walter, Marcelo

doi:10.1007/978-3-030-41590-7_1

Cited by 2 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Building upon this work, Jie Li et al 16,17 allocate fractions gathered from authentic woodcut textures according to segmented areas, applying this method to Yunnan out-of-print woodcut. A recent study by Mesquita et al 18 proposes woodcut generation based on reaction-diffusion, enhancing woodcut representation and user control by introducing noise. Current research in woodcut-style image generation primarily focuses on simulating woodcut marks, sidelining the artistic design aspect of woodcut.…”

Section: Woodcut-style Designmentioning

confidence: 99%

WDANet: exploring style feature via diffusion model for woodcut-style design

Ou,

2024

Preprint

View full text Add to dashboard Cite

Due to the strong visual impact and color contrast inherent in woodcut style design, it has been applied in animation and comics. However, traditional woodcuts, hand-drawn, and previous computer-aided methods have yet to address the issues of dwindling design inspiration, lengthy production times, and complex adjustment procedures. We propose a novel network framework, the Woodcut-style Design Assistant Network (WDANet), to tackle these challenges. Notably, our research is the first to utilize diffusion models to streamline the woodcut-style design process. We curate the Woodcut-62 dataset, which features works from 62 renowned historical artists, to train WDANet in absorbing and learning the aesthetic nuances of woodcut prints, offering users a wealth of design references. Based on a denoising network, our WDANet effectively integrates text and woodcut-style image features. WDANet allows users to input or slightly modify a text description to quickly generate accurate, high-quality woodcut-style designs, saving time and offering flexibility. As confirmed by user studies, quantitative and qualitative analyses show that WDANet outperforms the current state-of-the-art in generating woodcut-style images and proves its value as a design aid.

show abstract

Section: Woodcut-style Designmentioning

confidence: 99%

WDANet: exploring style feature via diffusion model for woodcut-style design

Ou,

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Building upon this work, Jie Li et al [19,20] allocate fractions gathered from authentic woodcut textures according to segmented areas, applying this method to Yunnan out-of-print woodcut. A recent study by Mesquita et al [21] proposes woodcut generation based on reaction-diffusion, enhancing woodcut representation and user control by introducing noise.…”

Section: Woodcut-style Designmentioning

confidence: 99%

WDANet: Exploring Style Feature via Dual Cross-Attention for Woodcut-Style Design

Ou,

2023

Preprint

View full text Add to dashboard Cite

People are drawn to woodcut-style designs due to their striking visual impact and strong contrast. However, traditional woodcut prints and previous computer-aided methods have not addressed the issues of dwindling design inspiration, lengthy production times, and complex adjustment procedures. We propose a novel network framework, the Woodcut-style Design Assistant Network (WDANet), to tackle these challenges. Notably, our research is the first to utilize diffusion models to streamline the woodcut-style design process. We've curated the Woodcut-62 dataset, featuring works from 62 renowned historical artists, to train WDANet in absorbing and learning the aesthetic nuances of woodcut prints, offering users a wealth of design references. Based on a noise reduction network, our dual cross-attention mechanism effectively integrates text and woodcut-style image features. This allows users to input or slightly modify a text description to quickly generate accurate, high-quality woodcut-style designs, saving time and offering flexibility. As confirmed by user studies, quantitative and qualitative analyses show that WDANet outperforms the current state-of-the-art in generating woodcut-style images and proves its value as a design aid.

show abstract

Synthesis and Validation of Virtual Woodcuts Generated with Reaction-Diffusion

Cited by 2 publications

References 38 publications

WDANet: exploring style feature via diffusion model for woodcut-style design

WDANet: exploring style feature via diffusion model for woodcut-style design

WDANet: Exploring Style Feature via Dual Cross-Attention for Woodcut-Style Design

Contact Info

Product

Resources

About