Litcius/Paper detail

Deep Generative Inpainting with Comparative Sample Augmentation

Boli Fang, Miao Jiang, Jerry Shen, Björn Stenger

2022Journal of Computational and Cognitive Engineering44 citationsDOIOpen Access PDF

Abstract

Recent advances in deep learning techniques such as Convolutional Neural Networks (CNN) and Generative Adversarial Networks (GAN) have achieved breakthroughs in the problem of semantic image inpainting, the task of reconstructing missing pixels. While more effective than conventional approaches, deep learning models require large datasets and computational resources for training, and inpainting quality varies considerably when training data differs in size and diversity. To address these problems, we present an inpainting strategy called Comparative Sample Augmentation, which enhances the quality of the training set by filtering irrelevant images and constructing additional images using information about the surrounding regions of the target image. Experiments on multiple datasets demonstrate that our method extends the applicability of deep inpainting models to training sets with varying levels of diversity, while enhancing the inpainting quality as measured by qualitative and quantitative metrics for a large class of deep models, with little need for model-specific consideration.

Topics & Concepts

InpaintingArtificial intelligenceDeep learningComputer scienceConvolutional neural networkSample (material)Generative grammarImage (mathematics)Pattern recognition (psychology)PixelSet (abstract data type)Quality (philosophy)Task (project management)Artificial neural networkMachine learningComputer visionPhilosophyManagementEconomicsEpistemologyProgramming languageChromatographyChemistryGenerative Adversarial Networks and Image SynthesisAdvanced Image Processing TechniquesAdvanced Neural Network Applications