paper-with-me

홈 › Papers

PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework

2025-06-12 · Sixiang Chen, Jianyu Lai, Jialin Gao, Tian Ye, Haoyu Chen, Hengyu Shi, Shitong Shao, Yunlong Lin, Song Fei, Zhaohu Xing, Yeying Jin, Junfeng Luo, Xiaoming Wei, Lei Zhu

Generating aesthetic posters is more challenging than simple design images: it requires not only precise text rendering but also the seamless integration of abstract artistic content, striking layouts, and overall stylistic harmony. To address this, we propose PosterCraft, a unified framework that abandons prior modular pipelines and rigid, predefined layouts, allowing the model to freely explore coherent, visually compelling compositions. PosterCraft employs a carefully designed, cascaded workflow to optimize the generation of high-aesthetic posters: (i) large-scale text-rendering optimization on our newly introduced Text-Render-2M dataset; (ii) region-aware supervised fine-tuning on HQ-Poster100K; (iii) aesthetic-text-reinforcement learning via best-of-n preference optimization; and (iv) joint vision-language feedback refinement. Each stage is supported by a fully automated data-construction pipeline tailored to its specific needs, enabling robust training without complex architectural modifications. Evaluated on multiple experiments, PosterCraft significantly outperforms open-source baselines in rendering accuracy, layout coherence, and overall visual appeal-approaching the quality of SOTA commercial systems. Our code, models, and datasets can be found in the Project page: https://ephemeral182.github.io/PosterCraft

📄 PDF Abstract BibTeX arXiv:2506.10741

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

POSTA: A Go-to Framework for Customized Artistic Poster Generation

2025-03-19 · CVPR 2025 1 · Haoyu Chen, Xiaojie Xu, Wenbo Li, Jingjing Ren 외

Poster design is a critical medium for visual communication. Prior work has explored automatic poster design using deep learning techniques, but these approaches lack text accuracy, user customization, and aesthetic appe…

Text Segmentation

PosterOmni: Generalized Artistic Poster Creation via Task Distillation and Unified Reward Feedback

2026-02-12 · Sixiang Chen, Jianyu Lai, Jialin Gao, Hengyu Shi 외 arxiv

Image-to-poster generation is a high-demand task requiring not only local adjustments but also high-level design understanding. Models must generate text, layout, style, and visual elements while preserving semantic fide…

PosterGen: Aesthetic-Aware Multi-Modal Paper-to-Poster Generation via Multi-Agent LLMs

2025-08-24 · Zhilin Zhang, Xiang Zhang, Jiaqi Wei, Yiwei Xu 외 arxiv

Multi-agent systems built upon large language models (LLMs) have demonstrated remarkable capabilities in tackling complex compositional tasks. In this work, we apply this paradigm to the paper-to-poster generation proble…

LeX-Art: Rethinking Text Generation via Scalable High-Quality Data Synthesis

2025-03-27 · Shitian Zhao, Qilong Wu, Xinyue Li, Bo Zhang 외

We introduce LeX-Art, a comprehensive suite for high-quality text-image synthesis that systematically bridges the gap between prompt expressiveness and text rendering fidelity. Our approach follows a data-centric paradig…

Image GenerationText Generation

AesthetiQ: Enhancing Graphic Layout Design via Aesthetic-Aware Preference Alignment of Multi-modal Large Language Models

2025-03-01 · CVPR 2025 1 · Sohan Patnaik, Rishabh Jain, Balaji Krishnamurthy, Mausoom Sarkar

Visual layouts are essential in graphic design fields such as advertising, posters, and web interfaces. The application of generative models for content-aware layout generation has recently gained traction. However, thes…

Large Language ModelLayout DesignLayout Generation