New AI Imaging Technique Reconstructs Photos With Realistic Results

New AI Imaging Technique Reconstructs Photos with Realistic Results

To prepare to train their neural network, the team first generated 55,116 masks of random streaks and holes of arbitrary shapes and sizes for training. They also generated nearly 25,000 for testing. These were further categorized into six categories based on sizes relative to the input image, in order to improve reconstruction accuracy.

Source: nvidia.com