Light field image angular domain super-resolution system and method based on zero sample learning

Abstract

The invention discloses a light field image angular domain super-resolution system and method based on zero sample learning. The light field image angular domain super-resolution system is composed ofa light field image acquisition module, a data preprocessing module, a network training module, a light field image super-resolution module and a data storage module. According to the system and themethod disclosed in the invention, a zero-sample learning idea is adopted to solve the problem of light field image angular domain super-resolution, and a light field image angular domain super-resolution function is realized in a self-adaptive manner according to the characteristics of different light field images.

Description

technical field

[0001] The invention belongs to the field of image technology, and in particular relates to a zero-sample learning-based light field image angle domain super-resolution system and method. Background technique

[0002] Traditional cameras can only collect the light intensity information of the scene, but lose the direction information of the light, so the three-dimensional structure information of the scene cannot be obtained. Traditional cameras force computers to observe the three-dimensional world only through two-dimensional images, which has brought bottlenecks to many vision applications. Compared with traditional cameras, light field cameras can simultaneously collect two-dimensional spatial domain and two-dimensional angular domain information of the scene, and use the rich angular domain information to obtain depth information and material information of objects, providing a better solution for scene understanding, virtual reality and other applicatio...

Images