Contour-guided Image Completion with Perceptual Grouping

TL;DR

This paper modernizes the Stochastic Completion Fields algorithm to improve contour completion and inpainting in images, mimicking human perceptual grouping, and enhances edge detection in noisy environments.

Contribution

It introduces a modernized SCF model integrated into an image editing framework, demonstrating improved contour completion, inpainting guidance, and noise robustness, aligning with human visual perception.

Findings

SCF-based contours improve inpainting results

Guided inpainting outperforms state-of-the-art models

SCF enhances edge detection in noisy images

Abstract

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.