CVAINov 22, 2021

Contour-guided Image Completion with Perceptual Grouping

arXiv:2111.11322v13 citations
Originality Incremental advance
AI Analysis

This work addresses image completion and editing tasks for computer vision applications, offering a novel framework that integrates perceptual grouping principles.

The paper tackled the problem of completing fragmented contours in images by modernizing the Stochastic Completion Fields algorithm, which mimics human perceptual grouping, and used it to guide inpainting, improving state-of-the-art model performance.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes