From Elements to Design: A Layered Approach for Automatic Graphic Design Composition
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915081434955776 |
|---|---|
| author | Lin, Jiawei Sun, Shizhao Huang, Danqing Liu, Ting Li, Ji Bian, Jiang |
| author_facet | Lin, Jiawei Sun, Shizhao Huang, Danqing Liu, Ting Li, Ji Bian, Jiang |
| contents | In this work, we investigate automatic design composition from multimodal graphic elements. Although recent studies have developed various generative models for graphic design, they usually face the following limitations: they only focus on certain subtasks and are far from achieving the design composition task; they do not consider the hierarchical information of graphic designs during the generation process. To tackle these issues, we introduce the layered design principle into Large Multimodal Models (LMMs) and propose a novel approach, called LaDeCo, to accomplish this challenging task. Specifically, LaDeCo first performs layer planning for a given element set, dividing the input elements into different semantic layers according to their contents. Based on the planning results, it subsequently predicts element attributes that control the design composition in a layer-wise manner, and includes the rendered image of previously generated layers into the context. With this insightful design, LaDeCo decomposes the difficult task into smaller manageable steps, making the generation process smoother and clearer. The experimental results demonstrate the effectiveness of LaDeCo in design composition. Furthermore, we show that LaDeCo enables some interesting applications in graphic design, such as resolution adjustment, element filling, design variation, etc. In addition, it even outperforms the specialized models in some design subtasks without any task-specific training. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_19712 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | From Elements to Design: A Layered Approach for Automatic Graphic Design Composition Lin, Jiawei Sun, Shizhao Huang, Danqing Liu, Ting Li, Ji Bian, Jiang Computer Vision and Pattern Recognition In this work, we investigate automatic design composition from multimodal graphic elements. Although recent studies have developed various generative models for graphic design, they usually face the following limitations: they only focus on certain subtasks and are far from achieving the design composition task; they do not consider the hierarchical information of graphic designs during the generation process. To tackle these issues, we introduce the layered design principle into Large Multimodal Models (LMMs) and propose a novel approach, called LaDeCo, to accomplish this challenging task. Specifically, LaDeCo first performs layer planning for a given element set, dividing the input elements into different semantic layers according to their contents. Based on the planning results, it subsequently predicts element attributes that control the design composition in a layer-wise manner, and includes the rendered image of previously generated layers into the context. With this insightful design, LaDeCo decomposes the difficult task into smaller manageable steps, making the generation process smoother and clearer. The experimental results demonstrate the effectiveness of LaDeCo in design composition. Furthermore, we show that LaDeCo enables some interesting applications in graphic design, such as resolution adjustment, element filling, design variation, etc. In addition, it even outperforms the specialized models in some design subtasks without any task-specific training. |
| title | From Elements to Design: A Layered Approach for Automatic Graphic Design Composition |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.19712 |