SAMVG: A Multi-stage Image Vectorization Model with the Segment-Anything Model
Abstract: Vector graphics are widely used in graphical designs and have received more and more attention. However, unlike raster images which can be easily obtained, acquiring high-quality vector graphics, typically through automatically converting from raster images remains a significant challenge, especially for more complex images such as photos or artworks. In this paper, we propose SAMVG, a multi-stage model to vectorize raster images into SVG (Scalable Vector Graphics). Firstly, SAMVG uses general image segmentation provided by the Segment-Anything Model and uses a novel filtering method to identify the best dense segmentation map for the entire image. Secondly, SAMVG then identifies missing components and adds more detailed components to the SVG. Through a series of extensive experiments, we demonstrate that SAMVG can produce high quality SVGs in any domain while requiring less computation time and complexity compared to previous state-of-the-art methods.
- “Image vectorization using optimized gradient meshes,” ACM Transactions on Graphics (TOG), vol. 26, no. 3, pp. 11–es, 2007.
- “Diffusion curves: a vector representation for smooth-shaded images,” ACM Transactions on Graphics (TOG), vol. 27, no. 3, pp. 1–8, 2008.
- “Hierarchical diffusion curves for accurate automatic image vectorization,” ACM Transactions on Graphics (TOG), vol. 33, no. 6, pp. 1–11, 2014.
- “Towards layer-wise image vectorization,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 16314–16323.
- “Differentiable vector graphics rasterization for editing and learning,” ACM Transactions on Graphics (TOG), vol. 39, no. 6, pp. 1–15, 2020.
- “DeepSVG: A hierarchical generative network for vector graphics animation,” Advances in Neural Information Processing Systems, vol. 33, pp. 16351–16361, 2020.
- “Deep vectorization of technical drawings,” in European Conference on Computer Vision. Springer, 2020, pp. 582–598.
- “A learned representation for scalable vector graphics,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019, pp. 7930–7939.
- “ClipGen: A deep generative model for clipart vectorization and synthesis,” IEEE Transactions on Visualization and Computer Graphics, vol. 28, no. 12, pp. 4211–4224, 2021.
- “Im2Vec: Synthesizing vector graphics without vector supervision,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 7342–7351.
- “Stroke-based neural painting and stylization with dynamically predicted painting region,” arXiv preprint arXiv:2309.03504, 2023.
- “Vectorization of raster manga by deep reinforcement learning,” arXiv preprint arXiv:2110.04830, 2021.
- “Effective clipart image vectorization through direct optimization of bezigons,” IEEE Transactions on Visualization and Computer Graphics, vol. 22, no. 2, pp. 1063–1075, 2015.
- James Richard Diebel, Bayesian Image Vectorization: the probabilistic inversion of vector image rasterization, Ph.D. thesis, Stanford University, 2008.
- Peter Selinger, “Potrace: a polygon-based tracing algorithm,” 2003.
- “Segment anything,” arXiv preprint arXiv:2304.02643, 2023.
- Yizong Cheng, “Mean shift, mode seeking, and clustering,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 8, pp. 790–799, 1995.
- “An automatic algorithm for approximating boundary of bitmap characters,” Future Generation Computer Systems, vol. 20, no. 8, pp. 1327–1336, 2004.
- “The unreasonable effectiveness of deep features as a perceptual metric,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 586–595.
- “Computing aesthetics,” in Brazilian Symposium on Artificial Intelligence. Springer, 1998, pp. 219–228.
- Gregory K Wallace, “The JPEG still picture compression standard,” Communications of the ACM, vol. 34, no. 4, pp. 30–44, 1991.
Paper Prompts
Sign up for free to create and run prompts on this paper.