Learning to Infer Graphics Programs from Hand-Drawn Images

Kevin Ellis, Daniel Ritchie, Armando Solar-Lezama, Joshua B. Tenenbaum

Feb 15, 2018 (modified: Feb 15, 2018) ICLR 2018 Conference Blind Submission readers: everyone Show Bibtex
  • Abstract: We introduce a model that learns to convert simple hand drawings into graphics programs written in a subset of \LaTeX.~The model combines techniques from deep learning and program synthesis. We learn a convolutional neural network that proposes plausible drawing primitives that explain an image. These drawing primitives are like a trace of the set of primitive commands issued by a graphics program. We learn a model that uses program synthesis techniques to recover a graphics program from that trace. These programs have constructs like variable bindings, iterative loops, or simple kinds of conditionals. With a graphics program in hand, we can correct errors made by the deep network and extrapolate drawings. Taken together these results are a step towards agents that induce useful, human-readable programs from perceptual input.
  • TL;DR: Learn to convert a hand drawn sketch into a high-level program
  • Keywords: program induction, HCI, deep learning