1. Input image
The artificial intelligence system automatically recognizes unclear image content.
3. AI “Brain Supplement” image content
Detailing with “spliced generation network” and “fixed point generation network”
4. Discriminator Multi-Round Optimization
The discriminator identifies the pros and cons of the finished product through human visually sensitive features and performs multiple rounds of optimization.
Modeling the aesthetic mathematics of humans and artists, creating objective functions such as ConcatGAN (splicing generation network) and InvarianceGAN (fixed point generation network)
n response to the characteristics of the film and television industry, the traditional CNN data was changed to a multiple cycle at a time, and the computing power was exchanged for higher image processing quality. Created a new model structure, LoopNet (circular network), Discriminator assisted final descent (discriminator-assisted convergence) to enable the network to improve output quality through multiple rounds of optimizatio
Used to make up for the shortcomings of existing neural network components, especially convolutional networks. This includes local gradient statistics extraction.
It is a way of preserving prior knowledge in neural networks, and it solves the problem of total knowledge limit due to the limitation of network computing being limited by objective computational power.
SD Video → 2K (processing 26 ’45”)
Remove the original picture scene effect
Removing deformed moir and sawtooth
Filling of picture details
Increase resolution: 720*576→1920*1080
Improve picture detail