# Contour-guided Image Completion with Perceptual Grouping

arXiv: https://arxiv.org/abs/2111.11322 · HTML: https://mlsanity.com/paper/2111.11322/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 38 references that are in the map.
- First posted on arXiv 22 Nov 2021.

## Builds on (most cited first, 8 of 8)

- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Generative Image Inpainting with Contextual Attention](https://mlsanity.com/paper/1801.07892/) (2018)
- [Deeply supervised salient object detection with short connections](https://mlsanity.com/paper/1611.04849/) (2016)
- [EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning](https://mlsanity.com/paper/1901.00212/) (2019)
- [Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection](https://mlsanity.com/paper/1909.01955/) (2019)
- [Foreground-aware Image Inpainting](https://mlsanity.com/paper/1901.05945/) (2019)
- [Appearance Shock Grammar for Fast Medial Axis Extraction from Real Images](https://mlsanity.com/paper/2004.02677/) (2020)
- [Scene Categorization from Contours: Medial Axis Based Salience Measures](https://mlsanity.com/paper/1811.10524/) (2018)

## Built on by (most cited first, 2 of 2)

- [Contour Completion using Deep Structural Priors](https://mlsanity.com/paper/2302.04447/) (2023)
- [Human Perception-Inspired Grain Segmentation Refinement Using Conditional Random Fields](https://mlsanity.com/paper/2312.09968/) (2023)

## Abstract (arXiv)

Humans are excellent at perceiving illusory outlines. We are readily able to complete contours, shapes, scenes, and even unseen objects when provided with images that contain broken fragments of a connected appearance. In vision science, this ability is largely explained by perceptual grouping: a foundational set of processes in human vision that describes how separated elements can be grouped. In this paper, we revisit an algorithm called Stochastic Completion Fields (SCFs) that mechanizes a set of such processes -- good continuity, closure, and proximity -- through contour completion. This paper implements a modernized model of the SCF algorithm, and uses it in an image editing framework where we propose novel methods to complete fragmented contours. We show how the SCF algorithm plausibly mimics results in human perception. We use the SCF completed contours as guides for inpainting, and show that our guides improve the performance of state-of-the-art models. Additionally, we show that the SCF aids in finding edges in high-noise environments. Overall, our described algorithms resemble an important mechanism in the human visual system, and offer a novel framework that modern computer vision models can benefit from.