Hierarchical Approach Towards High Fidelity Image Generation

Author(s):  
Arindam Chaudhuri ◽  
Soumya K. Ghosh
2001 ◽  
Author(s):  
Johann Arbocz ◽  
James Starnes ◽  
Michael Nemeth

2020 ◽  
Vol 2020 (8) ◽  
pp. 86-1-86-7
Author(s):  
Ayush Soni ◽  
Alexander Loui ◽  
Scott Brown ◽  
Carl Salvaggio

In this paper, we demonstrate the use of a Conditional Generative Adversarial Networks (cGAN) framework for producing high-fidelity, multispectral aerial imagery using low-fidelity imagery of the same kind as input. The motivation behind is that it is easier, faster, and often less costly to produce low-fidelity images than high-fidelity images using the various available techniques, such as physics-driven synthetic image generation models. Once the cGAN network is trained and tuned in a supervised manner on a data set of paired low- and high-quality aerial images, it can then be used to enhance new, lower-quality baseline images of similar type to produce more realistic, high-fidelity multispectral image data. This approach can potentially save significant time and effort compared to traditional approaches of producing multispectral images.


2018 ◽  
Vol 17 (3) ◽  
pp. 155-160 ◽  
Author(s):  
Daniel Dürr ◽  
Ute-Christine Klehe

Abstract. Faking has been a concern in selection research for many years. Many studies have examined faking in questionnaires while far less is known about faking in selection exercises with higher fidelity. This study applies the theory of planned behavior (TPB; Ajzen, 1991 ) to low- (interviews) and high-fidelity (role play, group discussion) exercises, testing whether the TPB predicts reported faking behavior. Data from a mock selection procedure suggests that candidates do report to fake in low- and high-fidelity exercises. Additionally, the TPB showed good predictive validity for faking in a low-fidelity exercise, yet not for faking in high-fidelity exercises.


Sign in / Sign up

Export Citation Format

Share Document