# Physically Embodied Deep Image Optimisation

arXiv: https://arxiv.org/abs/2201.08142 · HTML: https://mlsanity.com/paper/2201.08142/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 9 references that are in the map.
- First posted on arXiv 20 Jan 2022.

## Builds on (most cited first, 6 of 6)

- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [A Neural Algorithm of Artistic Style](https://mlsanity.com/paper/1508.06576/) (2015)
- [CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Norms](https://mlsanity.com/paper/1706.07068/) (2017)
- [Synthesizing Programs for Images using Reinforced Adversarial Learning](https://mlsanity.com/paper/1804.01118/) (2018)
- [Neural Painters: A learned differentiable constraint for generating brushstroke paintings](https://mlsanity.com/paper/1904.08410/) (2019)
- [Differentiable Drawing and Sketching](https://mlsanity.com/paper/2103.16194/) (2021)

## Abstract (arXiv)

Physical sketches are created by learning programs to control a drawing robot. A differentiable rasteriser is used to optimise sets of drawing strokes to match an input image, using deep networks to provide an encoding for which we can compute a loss. The optimised drawing primitives can then be translated into G-code commands which command a robot to draw the image using drawing instruments such as pens and pencils on a physical support medium.