Boundless: Generative Adversarial Networks for Image Extension

2019/08/19 by Piotr Teterwak, Aaron Sarna, Teterwak, Piotr +11 · 2 citations
Computer Science · #Generative Adversarial Networks and Image Synthesis #Advanced Image Processing Techniques #Computer Graphics and Visualization Techniques

paper · pdf · doi:10.48550/arxiv.1908.07007

Abstract

Image extension models have broad applications in image editing, computational photography and computer graphics. While image inpainting has been extensively studied in the literature, it is challenging to directly apply the state-of-the-art inpainting methods to image extension as they tend to generate blurry or repetitive pixels with inconsistent semantics. We introduce semantic conditioning to the discriminator of a generative adversarial network (GAN), and achieve strong results on image extension with coherent semantics and visually pleasing colors and textures. We also show promising results in extreme extensions, such as panorama generation.

Citations

• Auto-Encoding Variational Bayes

Cited by

• Rectification Reimagined: A Unified Mamba Model for Image Correction and Rectangling with Prompts
• Boosting Image Outpainting with Semantic Layout Prediction

Related

• Semantic Image Completion and Enhancement using GANs
• Image Outpainting and Harmonization using Generative Adversarial Networks
• Eye In-Painting with Exemplar Generative Adversarial Networks
• Pixel-wise Conditioning of Generative Adversarial Networks
• Context-Aware Semantic Inpainting