Reviews: Learning to Infer Graphics Programs from Hand-Drawn Images

Summary The paper presents a two-stage method to infer programs that generate input drawings. Initially, a CNN architecture is applied to translate the drawing into a sequence of primitive draw commands (lines, rectangles, circles, etc). Then, a program synthesizer is used to collapse the straight-line program into a proper program with conditionals and loops. First, let me say that I absolutely love the results of this paper. It is a wonderful combination of relatively simple tools to achieve something unexpected.