Abstract
Low-polygon image representation is commonly employed into simplify an image to reduced geometrical data. This paper proposes a method to generate a low-poly image from an AI-generated image. The proposed framework is based on a two-level simplification technique to achieve a considerable reduction in resolution while maintaining good visual quality. First, significant feature points are extracted from the segmented portions of the AI-generated image to obtain essential structural information. Subsequently, hexagonal grid-based sampling, which allows for the identification of crucial seed points while respecting significant visual elements, is employed. The Low-poly style is achieved through Delaunay triangulation, and the colors are taken directly from the original AI image to ensure visual consistency. Furthermore, we have compared the performance of entropy and saliency maps when used in the selection process for the hexagonal grid. We present experimental results demonstrating a pixel-to-point reduction of over 99.1%, as well as the ability to compress high-resolution images into a few simple points in a way that powerfully preserves perceptual integrity. Both qualitative and quantitative analyses were conducted on the AI-generated images at multiple resolutions, observing the sensitivity and scalability of the method for generating low-poly images.
References
[Online], Available: https://www.adobe.com/products/firefly.html
[Online], Available: https://openai.com/index/dall-e-3/
[Online], Available: https://www.canva.com/
[Online], Available: https://www.meta.ai/
[Online], Available: https://stabledifffusion.com/
Gai, Meng, and Guoping Wang. "Artistic low poly rendering for images." The visual computer 32 (2016): 491-500.
Topal, Cihan, and Cuneyt Akinlar. "Edge drawing: a combined real-time edge and segment detector." Journal of Visual Communication and Image Representation 23, no. 6 (2012): 862-872.
Zhang, Wenli, Shuangjiu Xiao, and Xin Shi. "Low-poly style image and video processing." In 2015 International Conference on Systems, Signals and Image Processing (IWSSIP), IEEE, 2015, 97-100.
C. J. Qian and D. Dobkin, “Generating low-poly abstractions,”[Online], Available: https://cjqian.github.io/docs/tri_iw_paper.pdf
Uasmith, Thitiwudh, Tantikorn Pukkaman, and Peeraya Sripian. "Low-poly image stylization." Journal for Geometry and Graphics 21, no. 1 (2017): 131-139.
Ma, Yiting, Xuejin Chen, and Yu Bai. "An interactive system for low-poly illustration generation from images using adaptive thinning." In 2017 IEEE International Conference on Multimedia and Expo (ICME), IEEE, 2017, 1033-1038.
Ng, Ruisheng, Lai-Kuan Wong, and John See. "Pic2geom: A fast rendering algorithm for low-poly geometric art." In Pacific Rim Conference on Multimedia, pp. 368-377. Cham: Springer International Publishing, 2017.
Lawonn, Kai, and Tobias Günther. "Stylized image triangulation." In Computer graphics forum, vol. 38, no. 1, 2019, 221-234.
Low, Pau-Ek, Lai-Kuan Wong, John See, and Ruisheng Ng. "Pic2PolyArt: Transforming a photograph into polygon-based geometric art." Signal Processing: Image Communication 91 (2021): 116090.
Laske, Olivia, and Lori Ziegelmeier. "Image Triangulation Using the Sobel Operator for Vertex Selection." arXiv preprint arXiv:2408.16112 (2024).
Joseph, Philumon, Binsu C. Kovoor, and Job Thomas. "Balancing Simplification and Detail Preservation in Low Poly Image Abstraction through Edge-Preserved Seed Point Generation." International Journal of Image, Graphics and Signal Processing (IJIGSP) 16, no. 2 (2024): 43-57.
Joseph, Philumon, Binsu C. Kovoor, and Job Thomas. "A Delaunay Triangulation-Based Low-Poly Image Abstraction." Journal of Image and Graphics 12, no. 4 (2024).
Dontmesswithtexas.org, “Don’t mess with Texas,”[Online], Available: https://www.dontmesswithtexas.org/.
Superhotgame.com, “SUPERHOT,”[Online], Available: https://superhotgame.com/.
Steampowered.com, “STEAM,”[Online], Available: https://store.steampowered.com/app/661740/Morphite/.
Astroneer.space, “ASTRONEER,”[Online], Available: https://astroneer.space/.
M. M. Keleşoğlu and D. GüleçÖzer, “A Study on Digital Low Poly Modeling Methods as an Abstraction Tool in Design Processes,” in Civil Engineering and Architecture, vol. 9, no.7,2021, 2570 – 2586.
Inkscape.org, “Inkscape,”[Online], Available: https://inkscape.org/.
Adobe.com, “Photo shop,”[Online], Available: https://www.adobe.com/products/photoshop. html.
Mould and Rosin, “A Benchmark Set for Evaluating Image Stylization,” Expressive 2016,[Online], Available: https://gigl.scs.carleton.ca/benchmark.html
Kaggle.com, “Natural Images,”[Online], Available: https://www.kaggle.com/code/navidrashik/object-detection-and-classification/data.
C. Zeng et al, “RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination,” ACM SIGGRAPH 2025.
Q. Wang, Z. Wang, K. Genova, P. P. Srinivasan, H. Zhou, J. T. Barron, R. Martin-Brualla, N. Snavely, and T. Funkhouser. “Ibrnet: Learning multi-view image-based rendering”. In CVPR. 2021, 4690–4699.
V. Sitzmann, S. Rezchikov, W. T. Freeman, J. B. Tenenbaum, and F. Durand. “Light field networks: neural scene representations with single-evaluation rendering.” In Proceedings of the 35th International Conference on Neural Information Processing Systems (NIPS '21). Curran Associates Inc., Red Hook, NY, USA, Article 1477, 2021, 19313–19325.
C. Wu, H. Mailee, Z. Montazeri, and T. Ritschel, “Learning to Rasterize Differentiably”. Computer Graphics Forum. vol.43(4), 2024.
T. M. Li, M. Lukač, M. Gharbi, and J. Ragan-Kelley, “Differentiable vector graphics rasterization for editing and learning”, ACM Transactions on Graphics (TOG), vol. 39(6), 2020, 1-15.
H. Yuan, A. Bousseau, H. Pan, Q. Zhang, N. J. Mitra ,L. Changjian , “DiffCSG: Differentiable CSG via Rasterization”, SIGGRAPH Asia 2024 Conference Papers Article No.: 9, 2024, 1 – 10.
S. Liu, W. Chen, T. Li and H. Li, "Soft Rasterizer: A Differentiable Renderer for Image-Based 3D Reasoning," IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), 2019, 7707-7716.
Q. Bammey, "Synthbuster: Towards Detection of Diffusion Model Generated Images," IEEE Open Journal of Signal Processing, vol. 5, 2024, 1-9.
Pixabay.com,[Online], Available: https://pixabay.com/