Wide-Context Semantic Image Extrapolation
Authors:
- 1 June 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1399-1408
Abstract
This paper studies the fundamental problem of extrapolating visual context using deep generative models, i.e., extending image borders with plausible structure and details. This seemingly easy task actually faces many crucial technical challenges and has its unique properties. The two major issues are size expansion and one-side constraints. We propose a semantic regeneration network with several special contributions and use multiple spatial related losses to address these issues. Our results contain consistent structures and high-quality textures. Extensive experiments are conducted on various possible alternatives and related methods. We also explore the potential of our method for various interesting applications that can benefit research in a variety of fields.Keywords
This publication has 37 references indexed in Scilit:
- Image Super-Resolution Using Deep Convolutional NetworksIEEE Transactions on Pattern Analysis and Machine Intelligence, 2015
- BiggerPictureACM Transactions on Graphics, 2014
- Rectangling panoramic images via warpingACM Transactions on Graphics, 2013
- FrameBreak: Dramatic Image Extrapolation by Guided Shift-Maps2013
- Quality prediction for image completionACM Transactions on Graphics, 2012
- Image meldingACM Transactions on Graphics, 2012
- A comparative study of image retargetingACM Transactions on Graphics, 2010
- Sketch2PhotoACM Transactions on Graphics, 2009
- PatchMatchACM Transactions on Graphics, 2009
- Image completion with structure propagationACM Transactions on Graphics, 2005