The Role of Edges in Line Drawing Perception
This addresses a theoretical problem in computer vision and perception research, but appears incremental as it builds on an existing hypothesis.
The paper tackles the problem of explaining line drawing perception by critiquing edge-based explanations and showing how the Realism Hypothesis resolves these issues, while also accounting for evidence that edges predict line drawings.
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.