# The Role of Edges in Line Drawing Perception

arXiv: https://arxiv.org/abs/2101.09376 · HTML: https://mlsanity.com/paper/2101.09376/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 30 references that are in the map.
- First posted on arXiv 22 Jan 2021.

## Builds on (most cited first, 4 of 4)

- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Understanding the Role of Individual Units in a Deep Neural Network](https://mlsanity.com/paper/2009.05041/) (2020)
- [Why Do Line Drawings Work? A Realism Hypothesis](https://mlsanity.com/paper/2002.06260/) (2020)
- [Neural Contours: Learning to Draw Lines from 3D Shapes](https://mlsanity.com/paper/2003.10333/) (2020)

## Built on by (most cited first, 3 of 3)

- [Learning to generate line drawings that convey geometry and semantics](https://mlsanity.com/paper/2203.12691/) (2022)
- [CLIPasso: Semantically-Aware Object Sketching](https://mlsanity.com/paper/2202.05822/) (2022)
- [PS-StyleGAN: Illustrative Portrait Sketching using Attention-Based Style Adaptation](https://mlsanity.com/paper/2409.00345/) (2024)

## Abstract (arXiv)

It has often been conjectured that the effectiveness of line drawings can be explained by the similarity of edge images to line drawings. This paper presents several problems with explaining line drawing perception in terms of edges, and how the recently-proposed Realism Hypothesis of Hertzmann (2020) resolves these problems. There is nonetheless existing evidence that edges are often the best features for predicting where people draw lines; this paper describes how the Realism Hypothesis can explain this evidence.