1. Light Field Synthesis by Training Deep Network in the Refocused Image Domain
- Author
-
Jiun-Woei Huang, Kuang-Tsu Shih, Homer H. Chen, and Chang-Le Liu
- Subjects
FOS: Computer and information sciences ,Image quality ,Structural similarity ,Computer science ,Computer Vision and Pattern Recognition (cs.CV) ,Computer Science - Computer Vision and Pattern Recognition ,ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION ,02 engineering and technology ,Image (mathematics) ,FOS: Electrical engineering, electronic engineering, information engineering ,0202 electrical engineering, electronic engineering, information engineering ,Angular resolution ,Computer vision ,Image sensor ,business.industry ,Image and Video Processing (eess.IV) ,Electrical Engineering and Systems Science - Image and Video Processing ,Computer Graphics and Computer-Aided Design ,Ray ,View synthesis ,020201 artificial intelligence & image processing ,Augmented reality ,Artificial intelligence ,business ,Software ,Light field - Abstract
Light field imaging, which captures spatio-angular information of incident light on image sensor, enables many interesting applications like image refocusing and augmented reality. However, due to the limited sensor resolution, a trade-off exists between the spatial and angular resolution. To increase the angular resolution, view synthesis techniques have been adopted to generate new views from existing views. However, traditional learning-based view synthesis mainly considers the image quality of each view of the light field and neglects the quality of the refocused images. In this paper, we propose a new loss function called refocused image error (RIE) to address the issue. The main idea is that the image quality of the synthesized light field should be optimized in the refocused image domain because it is where the light field is perceived. We analyze the behavior of RIL in the spectral domain and test the performance of our approach against previous approaches on both real and software-rendered light field datasets using objective assessment metrics such as MSE, MAE, PSNR, SSIM, and GMSD. Experimental results show that the light field generated by our method results in better refocused images than previous methods., Accepted to IEEE Transactions on Image Processing
- Published
- 2020
- Full Text
- View/download PDF