Where and Who? Automatic Semantic-Aware Person Composition
Autor: | Vicente Ordonez, Benjamin Cohen, Crispin Bernier, Fuwen Tan, Connelly Barnes |
---|---|
Rok vydání: | 2017 |
Předmět: |
FOS: Computer and information sciences
Computer science business.industry Computer Vision and Pattern Recognition (cs.CV) Computer Science - Computer Vision and Pattern Recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 02 engineering and technology Image segmentation 010501 environmental sciences 01 natural sciences Convolutional neural network Graphics (cs.GR) Computer Science - Graphics Fully automated restrict 0202 electrical engineering electronic engineering information engineering Task analysis 020201 artificial intelligence & image processing Computer vision Artificial intelligence User interface business 0105 earth and related environmental sciences Background image |
Zdroj: | WACV |
DOI: | 10.48550/arxiv.1706.01021 |
Popis: | Image compositing is a method used to generate realistic yet fake imagery by inserting contents from one image to another. Previous work in compositing has focused on improving appearance compatibility of a user selected foreground segment and a background image (i.e. color and illumination consistency). In this work, we instead develop a fully automated compositing model that additionally learns to select and transform compatible foreground segments from a large collection given only an input image background. To simplify the task, we restrict our problem by focusing on human instance composition, because human segments exhibit strong correlations with their background and because of the availability of large annotated data. We develop a novel branching Convolutional Neural Network (CNN) that jointly predicts candidate person locations given a background image. We then use pre-trained deep feature representations to retrieve person instances from a large segment database. Experimental results show that our model can generate composite images that look visually convincing. We also develop a user interface to demonstrate the potential application of our method. Comment: 10 pages, 9 figures |
Databáze: | OpenAIRE |
Externí odkaz: |