Nvidia
@nvidia·2.2M subscribers·2.7K videos
Research at NVIDIA: AI Reconstructs Photos with Realistic Results
Posted
April 23, 2018
Views
1,817,346
Likes
26,052
Engagement
1.43%
April 23, 2018
1,817,346
26,052
1.43%
Every word spoken in this episode is indexed. Type any phrase to jump straight to the moment it was said.
Type any word or phrase that may have been spoken. Click a result to seek the player to that exact moment.
Try a name, a topic, or a quoted line
2:15Now PlayingResearchers from NVIDIA, led by Guilin Liu, introduced a stateoftheart 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”
Sentinel Indexing in Progress
Metadata and chapters are available. Claim extraction for this episode is pending.
All video content is delivered via YouTube embedded players in accordance with the YouTube Terms of Service. Sentinel provides research tools that promote discovery and accountability across political media.
