
TL;DR
This paper critiques the edge-based explanation of line drawing perception, discusses the Realism Hypothesis as a solution, and explains how edges relate to human line drawing behavior.
Contribution
It analyzes limitations of edge-based theories and advocates for the Realism Hypothesis to better explain line drawing perception.
Findings
Edges often predict where people draw lines
The Realism Hypothesis addresses problems with edge explanations
Edges are significant features in line drawing perception
Abstract
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
