Optimize and Reduce: A Top-Down Approach for Image Vectorization
This addresses the need for fast, editable, and interpretable vector images across various domains, offering a significant improvement over prior methods.
The paper tackles the problem of raster-to-vector image conversion by proposing Optimize & Reduce (O&R), a top-down approach that achieves domain-agnostic performance, outperforming existing methods in reconstruction and perceptual quality for a fixed number of shapes, and is 10 times faster than the state-of-the-art optimization-based method.
Vector image representation is a popular choice when editability and flexibility in resolution are desired. However, most images are only available in raster form, making raster-to-vector image conversion (vectorization) an important task. Classical methods for vectorization are either domain-specific or yield an abundance of shapes which limits editability and interpretability. Learning-based methods, that use differentiable rendering, have revolutionized vectorization, at the cost of poor generalization to out-of-training distribution domains, and optimization-based counterparts are either slow or produce non-editable and redundant shapes. In this work, we propose Optimize & Reduce (O&R), a top-down approach to vectorization that is both fast and domain-agnostic. O&R aims to attain a compact representation of input images by iteratively optimizing Bézier curve parameters and significantly reducing the number of shapes, using a devised importance measure. We contribute a benchmark of five datasets comprising images from a broad spectrum of image complexities - from emojis to natural-like images. Through extensive experiments on hundreds of images, we demonstrate that our method is domain agnostic and outperforms existing works in both reconstruction and perceptual quality for a fixed number of shapes. Moreover, we show that our algorithm is $\times 10$ faster than the state-of-the-art optimization-based method.