Videos

Research at NVIDIA: AI Reconstructs Photos with Realistic Results



NVIDIA

Researchers from NVIDIA, led by Guilin Liu, 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. Learn more about their research paper “Image Inpainting for Irregular Holes Using Partial Convolutions”: https://nvda.ws/2K1G243

Source

Similar Posts

35 thoughts on “Research at NVIDIA: AI Reconstructs Photos with Realistic Results
  1. Researcher 1: Heyy, yeaaa its finished… but what does it do again?
    Researcher 2: Dont know bro, it… replaces? Stuff? Wiiiith something? Idk man just use it already.

  2. Photoshop can do most of this already, nividia just added face recognition and a library of facial features, that's it really, nothing new

  3. I hate to break it to you NVIDIA, but adobe Photoshop had used this tool called spot healing brush tool that does the same thing.

Comments are closed.

WP2Social Auto Publish Powered By : XYZScripts.com