Inspired by vector graphics software, Pix2vec learns to reconstruct a rasterized image by overlaying a finite number of layers of unique color. Similar to a human composing the image, the network iteratively predicts the next mask by looking at both the target image to reconstruct and the actual canvas.

How it works ?

We frame image generation as an alpha-blending composition of a sequence of layers. More precisely, we define our image generation procedure in a recurrent manner, given a fixed budget of T iterations. We start from an empty (black) canvas I0 and iteratively blend a total of T generated colored masks onto it.

How to cite


SBAI, Othman, COUPRIE, Camille, et AUBRY, Mathieu. Vector Image Generation by Learning Parametric Layer Decomposition. arXiv preprint arXiv:1812.05484, 2018.


  title={Vector Image Generation by Learning Parametric Layer Decomposition},
  author={Sbai, Othman and Couprie, Camille and Aubry, Mathieu},
  journal={arXiv preprint arXiv:1812.05484},