Generation of Stereo Images Based on a View Synthesis Network

Autor: Der-Lor Way, Chin-Chen Chang, Zen Chung Shih, Yuan Mau Lo
Rok vydání: 2020
Předmět:
neural network
Computer science
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Inpainting
Stereoscopy
02 engineering and technology
Translation (geometry)
lcsh:Technology
law.invention
Image (mathematics)
lcsh:Chemistry
law
depth estimation
0202 electrical engineering
electronic engineering
information engineering
General Materials Science
Computer vision
Image warping
lcsh:QH301-705.5
Instrumentation
Fluid Flow and Transfer Processes
Pixel
lcsh:T
business.industry
Process Chemistry and Technology
General Engineering
020207 software engineering
semantic segmentation
lcsh:QC1-999
Computer Science Applications
View synthesis
view synthesis
lcsh:Biology (General)
lcsh:QD1-999
lcsh:TA1-2040
Computer Science::Computer Vision and Pattern Recognition
020201 artificial intelligence & image processing
Artificial intelligence
stereo images
lcsh:Engineering (General). Civil engineering (General)
business
Rotation (mathematics)
lcsh:Physics
Zdroj: Applied Sciences, Vol 10, Iss 3101, p 3101 (2020)
Applied Sciences
Volume 10
Issue 9
ISSN: 2076-3417
DOI: 10.3390/app10093101
Popis: The conventional warping method only considers translations of pixels to generate stereo images. In this paper, we propose a model that can generate stereo images from a single image, considering both translation as well as rotation of objects in the image. We modified the appearance flow network to make it more general and suitable for our model. We also used a reference image to improve the inpainting method. The quality of images resulting from our model is better than that of images generated using conventional warping. Our model also better retained the structure of objects in the input image. In addition, our model does not limit the size of the input image. Most importantly, because our model considers the rotation of objects, the resulting images appear more stereoscopic when viewed with a device.
Databáze: OpenAIRE
Externí odkaz: