Simple AI image processing (deep image prior)
The deep image prior can be used for removal of gaps in an image (inpainting) and for denoising an image (noise reduction in early training epochs). The deep image prior can also be used for super resolution tasks.
No training data is needed, only the image data to process. Hence this is a very simple AI model for image processing, great as an introduction to deep learning and artificial intelligence (AI).
Link to main video: • Deep image prior: simple code for image re...
The deep image prior was proposed by Ulyanov, Vedaldi and Lempitsky in 2017.