Contour Completion using Deep Structural Priors
This work addresses a fundamental challenge in computer vision for tasks like object recognition and image inpainting, though it appears incremental as it builds on existing deep learning methods for structural completion.
The paper tackles the problem of contour completion in fragmented shapes by proposing a convolutional neural network framework that uses deep structural priors to connect disconnected lines and curves without needing to know which regions are missing, achieving results on a single image with no additional training data.
Humans can easily perceive illusory contours and complete missing forms in fragmented shapes. This work investigates whether such capability can arise in convolutional neural networks (CNNs) using deep structural priors computed directly from images. In this work, we present a framework that completes disconnected contours and connects fragmented lines and curves. In our framework, we propose a model that does not even need to know which regions of the contour are eliminated. We introduce an iterative process that completes an incomplete image and we propose novel measures that guide this to find regions it needs to complete. Our model trains on a single image and fills in the contours with no additional training data. Our work builds a robust framework to achieve contour completion using deep structural priors and extensively investigate how such a model could be implemented.