“Reconstructing Graphic Design Posters via Visual Decomposition and Semantic Layer Translation” by Avudaiappan and Murali
Conference:
Type(s):
Title:
- Reconstructing Graphic Design Posters via Visual Decomposition and Semantic Layer Translation
Session/Category Title:
- Images, Video & Computer Vision
Presenter(s)/Author(s):
Abstract:
This work presents a pipeline that converts rasterized graphic design posters into multi-layered, editable assets. It decomposes elements, addresses layer ordering using a novel Z-index strategy, and shows high accuracy through evaluations of over 24,000 posters. User feedback confirms its ability to accurately reconstruct posters with excellent fidelity.
References:
[1] Veeramanohar Avudaiappan and Ritwik Murali. 2025. Exploring Multi-objective Evolution for Aesthetic and Abstract 3D Art. In Artificial Intelligence in Music, Sound, Art and Design, Penousal Machado, Colin Johnson, and Iria Santos (Eds.). Springer Nature Switzerland, Cham, 261–277.
[2] Haoyu Chen, Xiaojie Xu, Wenbo Li, Jingjing Ren, Tian Ye, Songhua Liu, Ying-Cong Chen, Lei Zhu, and Xinchao Wang. 2025. POSTA: A Go-to Framework for Customized Artistic Poster Generation. arXiv preprint arXiv:https://arXiv.org/abs/2503.14908 (2025).
[3] Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Qing Jiang, Chunyuan Li, Jianwei Yang, Hang Su, Jun Zhu, and Lei Zhang. 2024. Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection. arxiv:https://arXiv.org/abs/2303.05499 [cs.CV] https://arxiv.org/abs/2303.05499
[4] Ritwik Murali and Veeramanohar Avudaiappan. 2024. Exploring Evolution for Aesthetic & Abstract 3D Art. In Proceedings of the Genetic and Evolutionary Computation Conference Companion. 691–694.
[5] Aoxiang Ning, Yiting Wei, Minglong Xue, and Senming Zhong. 2024. Artistic-style text detector and a new Movie-Poster dataset. arXiv preprint arXiv:https://arXiv.org/abs/2406.16307 (2024).
[6] Wataru Shimoda, Daichi Haraguchi, Seiichi Uchida, and Kota Yamaguchi. 2021. De-rendering Stylized Texts. In 2021 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, Montreal, QC, Canada, 1056–1065.
[7] Roman Suvorov, Elizaveta Logacheva, Anton Mashikhin, Anastasia Remizova, Arsenii Ashukha, Aleksei Silvestrov, Naejin Kong, Harshith Goka, Kiwoong Park, and Victor Lempitsky. 2021. Resolution-robust Large Mask Inpainting with Fourier Convolutions. arxiv:https://arXiv.org/abs/2109.07161 [cs.CV] https://arxiv.org/abs/2109.07161
[8] Youcai Zhang, Xinyu Huang, Jinyu Ma, Zhaoyang Li, Zhaochuan Luo, Yanchun Xie, Yuzhuo Qin, Tong Luo, Yaqian Li, Shilong Liu, et al. 2023. Recognize Anything: A Strong Image Tagging Model. arXiv preprint arXiv:https://arXiv.org/abs/2306.03514 (2023).
