A Deep Learning System That Removes Visual Noise From Digital Images by Looking at Pixelated Photos
Two Minute Papers took a comprehensive look at an amazing collaborative project between NVIDIA, Aalto University, and MIT that solves the problem of grainy digital photos. They developed a really intelligent AI system uses deep learning to smoothly remove visual noise from digital images by looking at pixelated photos.
Recent deep learning work in the field has focused on training a neural network to restore images by showing example pairs of noisy and clean images. The AI then learns how to make up the difference. This method differs because it only requires two input images with the noise or grain.
via The Awesomer
Related Laughing Squid Posts- NVIDIA Demonstrates New AI Technology for Reconstructing Photos With Realistic Results
- A Brilliantly Psychedelic Deep Machine Learning Interpretation of The Joy of Painting With Bob Ross
- 'Flying Formation', A Series of Digital Photo Collages of Birds Flying in Precise Geometric Formations
The post A Deep Learning System That Removes Visual Noise From Digital Images by Looking at Pixelated Photos appeared first on Laughing Squid.