Othman Sbai^{1,2},
Camille Couprie^{1},
Mathieu Aubry^{2},

^{1}Facebook AI Research,
^{2}LIGM (UMR 8049) - Ecole des Ponts, UPE

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.

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 I_{0} and iteratively blend a total of T generated colored masks onto it.

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

@article{sbai2018vector, title={Vector Image Generation by Learning Parametric Layer Decomposition}, author={Sbai, Othman and Couprie, Camille and Aubry, Mathieu}, journal={arXiv preprint arXiv:1812.05484}, year={2018} }