The top 5 AI nvidia achievements of 2018
Advancements in 2018 in AI : Photo's, Video, Graphics
NVIDIA named the top 5 AI achievements of 2018
5 – NVIDIA Invents AI Interactive Graphics
Nvidia Researchers developed a deep learning-based model that aims to catapult the graphics industry into the AI chapter. Using a conditional generative neural network, researchers rendered the first interactive world with from existing videos. This breakthrough will allow developers and artists to create new interactive 3D virtual worlds for automotive training, gaming, and VR.
4 – AI Algorithm Can Read Your Mind
Researchers from ATR Computational Neuroscience Laboratories and Kyoto University in Japan developed a deep learning-based algorithm that can generate images from brain activity.
The researchers trained their decoders on MRIs taken while human subjects looked at images over a ten-month period. The images included geometric shapes, natural phenomena and letters of the alphabet.
3 – Transforming Standard Video Into Slow Motion with AI
Researchers from NVIDIA developed a deep learning-based system that can produce high-quality slow-motion videos from a 30-frame-per-second video, outperforming various state-of-the-art methods that aim to do the same. The team trained their system on over 11,000 videos of everyday and sports activities shot at 240 frames-per-second.
To help demonstrate the research, the team used a variety of standard video clips including some from popular YouTubers, The SloMo Guys, and made them even slower.
2 – AI Can Fix Your Grainy Photos
This deep learning-based approach has learned to fix photos by simply looking at examples of corrupted photos only. The work was developed by researchers from NVIDIA, Aalto University, and MIT.
Without ever being shown what a noise-free image looks like, this AI can remove artifacts, noise, grain, and automatically enhance your photos.
1 – New AI Imaging Technique Reconstructs Photos
Researchers from NVIDIA introduced a state-of-the-art deep learning method that can edit images or reconstruct a corrupted image, one that has holes or is missing pixels.
The method can also be used to edit images by removing content and filling in the resulting holes.
The method, which performs a process called “image inpainting”, could be implemented in photo editing software to remove unwanted content, while filling it with a realistic computer-generated alternative.
Related Posts