Elamur Research⌕
☰
home / papers / 2026 / ReContraster: Making Your Posters Stand Out with Regional Contrast

ReContraster: Making Your Posters Stand Out with Regional Contrast

Paper · 2026 · Peixuan Zhang, Zijian Jia, Ziqi Cai et al.

Summary

ReContraster addresses a gap in text-to-poster generation. Current systems produce tidy layouts and legible text, but their posters rarely grab attention at a glance. The authors build on the "contrast effects" idea from perception research: viewers react strongly to opposing stimuli, such as ruined versus green landscapes. ReContraster is described as the first training-free pipeline that builds posters around regional contrast. The user supplies a description and a mask that splits the canvas into regions. Three LLM agents then mimic a designer's workflow:

  • a cognition agent proposes contrasting element pairs from the theme;
  • an arranger agent composes them into a JSON layout;
  • a refiner agent critiques generated candidates and loops back until satisfied.

A pre-trained diffusion model renders the image with a hybrid denoising scheme that smooths region seams. Visual text is then added using OpenCOLE's renderer. The authors also release a benchmark of images paired with descriptions and region-division annotations. Across seven automatic metrics and four user studies, the method beats prior systems. This suggests that agent-based reasoning about contrast can make posters both striking and harmonious.

Key points

  • Hybrid denoising:
    • Early diffusion steps use a gradient consistency loss that penalizes gradient mismatches across region borders.
    • Later steps use joint regional denoising, which linearly mixes the noise of neighbouring regions.
  • Baselines: PosterGen, OpenCOLE, SD3 and PosterMaker, among others. ReContraster reportedly leads on all seven metrics:
    • LAS (aesthetics; not the parsing metric of the same name);
    • RSD (element contrast);
    • BGD (boundary transitions);
    • OCR (text accuracy);
    • three VLM-judged scores: CRE, VAI and BIH.
  • User studies: run on Amazon Mechanical Turk with 100 benchmark samples and 25 volunteers. Each trial compared seven posters on four criteria: how strongly the elements contrasted, how continuous the content appeared, how precisely the regions were divided, and how well the text matched the image.
  • Ablations: four ablations confirm that each part contributes: agent interaction (CAI), the iterative refiner (IRA), GCL and JRD.
  • Applications: the system supports multilingual (e.g., Chinese) text, custom region masks and editing of user photos.
  • Limitation: quality drops when region divisions are very small or intricate.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Peking UniversityBeijing · China244 works · 39,359 citations🎓Beijing University of Posts and TelecommunicationsBeijing · China57 works · 32,843 citations🔬Beijing Academy of Artificial IntelligenceBeijing · China32 works · 7,511 citations

 Fields, topics and concepts

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 16,667 worksArts and Humanities · 16,039 worksComputer Vision and Pattern Recognition · 2,869 worksHistory and Philosophy of Science · 53 worksComputer Graphics and Computer-Aided Design · 7 works

Cite

Cite as Peixuan Zhang, Zijian Jia, Ziqi Cai, Shuchen Weng, Si Li and Boxin Shi. 2026. ReContraster: Making Your Posters Stand Out with Regional Contrast. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2026.acl-long.98

@inproceedings{zhang2026recontraster,
  title = {{ReContraster: Making Your Posters Stand Out with Regional Contrast}},
  author = {Peixuan Zhang, Zijian Jia, Ziqi Cai, Shuchen Weng, Si Li and Boxin Shi},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.98},
  url = {https://doi.org/10.18653/v1/2026.acl-long.98}
}

References

65 references, 20 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, and 1 others. 2023. GPT-4 technical report. arXiv preprint arXiv:2303.08774.
  2. Zheng Chang, Shuchen Weng, Peixuan Zhang, Yu Li, Si Li, and Boxin Shi. 2023. L-CAD: Language-based colorization with any-level descriptions using diffusion priors. In Advances in Neural Information Processing Systems. find
  3. Jingye Chen, Yupan Huang, Tengchao Lv, Lei Cui, Qifeng Chen, and Furu Wei. 2023. TextDiffuser: Diffusion models as text painters. In Advances in Neural Information Processing Systems. find
  4. Jingye Chen, Yupan Huang, Tengchao Lv, Lei Cui, Qifeng Chen, and Furu Wei. 2024a. TextDiffuser-2: Unleashing the power of language models for text rendering. In European Conference on Computer Vision. find
  5. Junsong Chen, Jincheng Yu, Chongjian Ge, Lewei Yao, Enze Xie, Yue Wu, Zhongdao Wang, James Kwok, Ping Luo, Huchuan Lu, and 1 others. 2024b. PixArt-α: Fast training of diffusion transformer for photorealistic text-to-image synthesis. In International Conference on Learning Representations. find
  6. Kanzhi Cheng, Qiushi Sun, Yougang Chu, Fangzhi Xu, Yantao Li, Jianbing Zhang, and Zhiyong Wu. 2024. Seeclick: Harnessing gui grounding for advanced visual gui agents. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics.
  7. Daniel Cohen-Or, Olga Sorkine, Ran Gal, Tommer Ley-vand, and Ying-Qing Xu. 2006. Color harmonization. In ACM SIGGRAPH Conference Papers. find
  8. Failure cases are presented in Sec. B Yang Deng, Xuan Zhang, Wenxuan Zhang, Yifei Yuan, See-Kiong Ng, and Tat-Seng Chua. 2024. On the multi-turn instruction following for conversational web agents. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. find
  9. Yingying Deng, Fan Tang, Weiming Dong, Chongyang Ma, Xingjia Pan, Lei Wang, and Changsheng Xu. 2022. Stytr2: Image style transfer with transformers. In IEEE/CVF Conference on Computer Vision and Pattern Recognition. find
  10. Ming Ding, Zhuoyi Yang, Wenyi Hong, Wendi Zheng, Chang Zhou, Da Yin, Junyang Lin, Xu Zou, Zhou Shao, Hongxia Yang, and 1 others. 2021. Cogview: Mastering text-to-image generation via transformers. In Advances in Neural Information Processing Systems.
  11. Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Amy Yang, Angela Fan, and 1 others. 2024. The llama 3 herd of models. arXiv e-prints, pages arXiv–2407.
  12. Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas Müller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, and 1 others. 2024. Scaling rectified flow transformers for high-resolution image synthesis. In International Conference on Machine Learning. find
  13. Yifan Gao, Zihang Lin, Chuanbin Liu, Min Zhou, Tiezheng Ge, Bo Zheng, and Hongtao Xie. 2025. Postermaker: Towards high-quality product poster generation with accurate text rendering. In IEEE/CVF Conference on Computer Vision and Pattern Recognition. find
  14. Jonathan Ho and Tim Salimans. 2022. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598.
  15. Hsiao Yuan Hsu, Xiangteng He, Yuxin Peng, Hao Kong, and Qing Zhang. 2023. PosterLayout: A new benchmark and approach for content-aware visual-textual presentation layout. In IEEE/CVF Conference on Computer Vision and Pattern Recognition. find
  16. Naoto Inoue, Kento Masui, Wataru Shimoda, and Kota Yamaguchi. 2024. OpenCOLE: Towards reproducible automatic graphic design generation. arXiv preprint arXiv:2406.08232. — [arXiv:2406.08232](https://arxiv.org/abs/2406.08232) find
  17. Peidong Jia, Chenxuan Li, Yuhui Yuan, Zeyu Liu, Yichao Shen, Bohan Chen, Xingru Chen, Yinglin Zheng, Dong Chen, Ji Li, and 1 others. 2023. COLE: A hierarchical generation framework for multi-layered and editable graphic design. arXiv preprint arXiv:2311.16974. — [arXiv:2311.16974](https://arxiv.org/abs/2311.16974) find
  18. Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C Berg, Wan-Yen Lo, and 1 others. 2023. Segment anything. In International Conference on Computer Vision. 2163 9
  19. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. In Advances in Neural Information Processing Systems.
  20. Black Forest Labs. 2024. Flux. https://github.com/ black-forest-labs/flux. ↗
  21. G Levkine. 2012. Prewitt, Sobel and Scharr gradient 5x5 convolution matrices. Image Process. Articles, Second Draft. find
  22. Zaijing Li, Gongwei Chen, Rui Shao, Dongmei Jiang, and Liqiang Nie. 2024. Enhancing the emotional generation capability of large language models via emotional chain-of-thought. arXiv preprint arXiv:2401.06836. — [arXiv:2401.06836](https://arxiv.org/abs/2401.06836) find
  23. Jiawei Lin, Jiaqi Guo, Shizhao Sun, Zijiang Yang, Jian-Guang Lou, and Dongmei Zhang. 2024. Layout-Prompter: Awaken the design ability of large language models. In Advances in Neural Information Processing Systems. find
  24. Jinpeng Lin, Min Zhou, Ye Ma, Yifan Gao, Chenxi Fei, Yangjian Chen, Zhang Yu, and Tiezheng Ge. 2023. AutoPoster: A highly automatic and content-aware design system for advertising poster generation. In ACM International Conference on Multimedia. find
  25. Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. In Advances in Neural Information Processing Systems.
  26. Yunbo Long, Yuhan Liu, and Liming Xu. 2026. Emomas: Emotion-aware multi-agent system for high-stakes edge-deployable negotiation with bayesian orchestration. arXiv preprint arXiv:2604.07003.
  27. Jian Ma, Yonglin Deng, Chen Chen, Haonan Lu, and Zhenyu Yang. 2025. Glyphdraw2: Automatic generation of complex glyph posters with diffusion models and large language models. In Association for the Advancement of Artificial Intelligence. find
  28. Anu MacIntosh-Murray. 2007. Poster presentations as a genre in knowledge communication: a case study of forms, norms, and values. Science communication. find
  29. Chong Mou, Xintao Wang, Liangbin Xie, Yanze Wu, Jian Zhang, Zhongang Qi, and Ying Shan. 2024. T2I-Adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models. In Association for the Advancement of Artificial Intelligence. find
  30. Zena O’Connor. 2015. Colour, contrast and gestalt theories of perception: The impact in contemporary visual communications design. Color Research & Application. find
  31. Jerry K Palmer and Jonathan S Gore. 2014. A theory of contrast effects in performance appraisal and social cognitive judgments. Psychological Studies. find
  32. Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas Müller, Joe Penna, and Robin Rombach. 2023. SDXL: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952.
  33. Shuofei Qiao, Ningyu Zhang, Runnan Fang, Yujie Luo, Wangchunshu Zhou, Yuchen Eleanor Jiang, Chengfei Lv, and Huajun Chen. 2024. Autoact: Automatic agent learning from scratch for qa via self-planning. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. find
  34. Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In International Conference on Machine Learning.
  35. Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Björn Ommer. 2022. High-resolution image synthesis with latent diffusion models. In IEEE/CVF Conference on Computer Vision and Pattern Recognition. find
  36. Laura D Scherer and Alan J Lambert. 2009. Contrast effects in priming paradigms: Implications for theory and research on implicit attitudes. Journal of personality and social psychology. find
  37. Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, and 1 others. 2022. LAION-5B: An open large-scale dataset for training next generation image-text models. In Advances in Neural Information Pr…
  38. Jaejung Seol, Seojun Kim, and Jaejun Yoo. 2024. PosterLlama: Bridging design ability of langauge model to contents-aware layout generation. arXiv preprint arXiv:2404.00995. — [arXiv:2404.00995](https://arxiv.org/abs/2404.00995) find
  39. Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In International Conference on Learning Representations.
  40. Rui Sun, Jie Ding, Chenghua Gong, Tianjun Gu, Yihang Jiang, Juyuan Zhang, Liming Pan, and Linyuan Lü. 2026. Topodim: One-shot topology generation of diverse interaction modes for multi-agent systems. arXiv preprint arXiv:2601.10120.
  41. Yuxiang Tuo, Wangmeng Xiang, Jun-Yan He, Yifeng Geng, and Xuansong Xie. 2024. AnyText: Multilingual visual text generation and editing. In International Conference on Learning Representations. find
  42. AW Utoyo, HD Aprilia, RADRI Kuntjoro-Jakti, and A Kurniawan. 2021. Visual communication design: Poster as an important way to encourage social distance in Jakarta when the epidemic 19. In IOP conference series: earth and environmental science. 2164 10 find
  43. Andrey Voynov, Kfir Aberman, and Daniel Cohen-Or. 2023. Sketch-guided text-to-image diffusion models. In ACM SIGGRAPH Conference Papers. find
  44. Zhenyu Wang, Aoxue Li, Zhenguo Li, and Xihui Liu. 2024a. Genartist: Multimodal LLM as an agent for unified image generation and editing. In Advances in Neural Information Processing Systems. find
  45. Zhouxia Wang, Xintao Wang, Liangbin Xie, Zhongang Qi, Ying Shan, Wenping Wang, and Ping Luo. 2024b. StyleAdapter: A unified stylized image generation model. International Journal of Computer Vision. find
  46. Ziqing Wang, Yibo Wen, William Pattie, Xiao Luo, Weimin Wu, Jerry Yao-Chieh Hu, Abhishek Pandey, Han Liu, and Kaize Ding. 2025a. Polo: Preference-guided multi-turn reinforcement learning for lead optimization. arXiv preprint arXiv:2509.21737. — [arXiv:2509.21737](https://arxiv.org/abs/2509.21737) find
  47. Ziqing Wang, Kexin Zhang, Zihan Zhao, Yibo Wen, Abhishek Pandey, Han Liu, and Kaize Ding. 2025b. A survey of large language models for text-guided molecular discovery: from molecule generation to optimization. arXiv preprint arXiv:2505.16094.
  48. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, and 1 others. 2022. Chain-of-thought prompting elicits reasoning in large language models. In Advances in Neural Information Processing Systems.
  49. Shuchen Weng, Peixuan Zhang, Zheng Chang, Xinlong Wang, Si Li, and Boxin Shi. 2023. Affective image filter: Reflecting emotions from text to images. In ICCV. find
  50. Meng Xu, Tong Zhang, Fuyun Wang, Yi Lei, Xin Liu, and Zhen Cui. 2024. MPDS: A movie posters dataset for image generation with diffusion model. arXiv preprint arXiv:2410.16840. — [arXiv:2410.16840](https://arxiv.org/abs/2410.16840) find
  51. Jintian Zhang, Xin Xu, Ningyu Zhang, Ruibo Liu, Bryan Hooi, and Shumin Deng. 2024. Exploring collaboration mechanisms for llm agents: A social psychology view. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics.
  52. Peixuan Zhang, Zijian Jia, Kaiqi Liu, Shuchen Weng, Si Li, and Boxin Shi. 2025b. Stage: Storyboard-anchored generation for cinematic multi-shot narrative. arXiv preprint arXiv:2512.12372. — [arXiv:2512.12372](https://arxiv.org/abs/2512.12372) find
  53. Peixuan Zhang, Shuchen Weng, Jiajun Tang, Si Li, and Boxin Shi. 2025c. Towards deeper emotional reflection: Crafting affective image filters with generative priors. IEEE transactions on pattern analysis and machine intelligence. find
  54. Peixuan Zhang, Shuchen Weng, Chengxuan Zhu, Binghao Tang, Zijian Jia, Si Li, and Boxin Shi. 2026a. Affective image editing: Shaping emotional factors via text descriptions. International Journal of Computer Vision, 134(1):16. find
  55. Peixuan Zhang, Chang Zhou, Ziyuan Zhang, Hualuo Liu, Chunjie Zhang, Jingqi Liu, Xiaohui Zhou, Xi Chen, Shuchen Weng, Si Li, and Boxin Shi. 2026b. A benchmark and multi-agent system for instruction-driven cinematic video compilation. arXiv preprint arXiv:2604.10456. — [arXiv:2604.10456](https://arxiv.org/abs/2604.10456) find
  56. Qianchi Zhang, Hainan Zhang, Liang Pang, Hongwei Zheng, and Zhiming Zheng. 2026c. Stable-rag: Mitigating retrieval-permutation-induced hallucinations in retrieval-augmented generation. arXiv preprint arXiv:2601.02993.
  57. Yunyao Zhang, Zikai Song, Hang Zhou, Wenfeng Ren, Yi-Ping Phoebe Chen, Junqing Yu, and Wei Yang. 2025d. ga − s 3 : Comprehensive social network simulation with group agents. In Findings of the Association for Computational Linguistics: ACL 2025. find
  58. Tao Yang, Yingmin Luo, Zhongang Qi, Yang Wu, Ying Shan, and Chang Wen Chen. 2024. PosterLLaVa: Constructing a unified multi-modal layout generator with LLM. arXiv preprint arXiv:2406.02884. — [arXiv:2406.02884](https://arxiv.org/abs/2406.02884) find
  59. Yunyao Zhang, Xinglang Zhang, Junxi Sheng, Wenbing Li, Junqing Yu, Yi-Ping Phoebe Chen, Wei Yang, and Zikai Song. 2025e. Semantic-aware logical reasoning via a semiotic framework. arXiv preprint arXiv:2509.24765.
  60. Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. React: Synergizing reasoning and acting in language models. In International Conference on Learning Representations.
  61. Yiming Zhao and Zhouhui Lian. 2024. UDiffText: A unified framework for high-quality text synthesis in arbitrary images via character-aware diffusion models. In European Conference on Computer Vision. find
  62. Hu Ye, Jun Zhang, Sibo Liu, Xiao Han, and Wei Yang. 2023. IP-Adapter: Text compatible image prompt adapter for text-to-image diffusion models.(2023). arXiv preprint arXiv:2308.06721. — [arXiv:2308.06721](https://arxiv.org/abs/2308.06721) find
  63. Hui Zhang, Dexiang Hong, Tingwei Gao, Yitong Wang, Jie Shao, Xinglong Wu, Zuxuan Wu, and Yu-Gang Jiang. 2025a. CreatiLayout: Siamese multimodal diffusion transformer for creative layout-to-image generation. In International Conference on Computer Vision. find
  64. Xinru Zheng, Xiaotian Qiao, Ying Cao, and Rynson WH Lau. 2019. Content-aware generative modeling of graphic design layouts. ACM TOG. find
  65. Min Zhou, Chenchen Xu, Ye Ma, Tiezheng Ge, Yuning Jiang, and Weiwei Xu. 2022. Composition-aware graphic layout GAN for visual-textual presentation designs. In International Joint Conference on Artificial Intelligence. 2165 11 find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zhang-2026-recontraster-making-your-posters-stand/