Gradient Descent in the ALPS: Abstracted Low-Poly Stylization and Fabrication
Ruben Wiersma, Alexandre Binninger, Peizhuo Li, Tanguy Magne, Annika Öhri, Aviv Segall, Danielle Luterbacher, Marcel Padilla, Jing Ren, Olga Sorkine-Hornung
Abstract
The low-poly style is a popular genre of vector graphics that depicts objects and scenes as flat-shaded meshes of low polygon count, often with a limited palette. In this paper, we propose a method to generate 2D low-poly meshes to abstract images. While it has been possible to achieve this look with general-purpose image generators and vector-based diffusion models, the resulting images are not guaranteed to be valid polygonal meshes. A key problem is that polygons overlap or intersect and, in the case of pixel-based image generators, the shapes are often not polygons. Moreover, the colors are not guaranteed to be constrained to a fixed palette. Aside from aesthetic considerations, this has practical consequences: it complicates editing and fabricating the results. We solve this problem by representing an image as a 2D polygonal mesh and optimizing the topology, geometry and coloring of the mesh using score distillation sampling, while enforcing geometric constraints, such as manifoldness and bijectivity. This presents unique challenges due to the discrete nature of the topology, which we handle using a fine-to-coarse strategy based on mesh simplification. By also constraining the colors to a fixed palette, we are able to produce various fabrications such as mosaics, embroidery, crocheting, patchwork and stencils from the resulting vector images. Code is at https://github.com/rubenwiersma/alps.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Builds on11
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- DreamFusion: Text-to-3D using 2D DiffusionBen Poole, Ajay Jain, Jonathan T. Barron, Ben MildenhallICLR 2023 · 463 citations
- Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and DenoisingJon Hasselgren, Nikolai Hofmann, Jacob MunkbergNeurIPS 2022 · 234 citations
- Flexible Isosurface Extraction for Gradient-Based Mesh OptimizationTianchang Shen, Jacob Munkberg, Jon Hasselgren, Kangxue Yin et al.SIGGRAPH 2023 · 100 citations
- SVGDreamer: Text Guided SVG Generation with Diffusion ModelXiming Xing, Haitao Zhou, Chuang Wang, Jing Zhang et al.CVPR 2024 · 22 citations
Related papers
- Layered Image Vectorization via Semantic SimplificationZhenyu Wang, Jianxi Huang, Zhida Sun, Yuanhao Gong et al.CVPR 2025
- Text-to-Vector Generation with Neural Path RepresentationPeiying Zhang, Nanxuan Zhao, Jing LiaoSIGGRAPH 2024 · 15 citations
- As-Plausible-As-Possible: Plausibility-Aware Mesh Deformation Using 2D Diffusion PriorsSeungwoo Yoo, Kunho Kim, Vladimir G. Kim, Minhyuk SungCVPR 2024 · 4 citations
- VecDesigner: Exploring Visual Guidance and Structural Consistency for Semantic TypographyLiu Yu, Xingjiao Wu, Ziang Liu, Jiabao Zhao et al.ICML 2026
- Generative Escher MeshesNoam Aigerman, Thibault GroueixSIGGRAPH 2024 · 8 citations
