Published
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
- Category
- NVIDIA
- Tags
- NVIDIA, AI, AI research
Be the first to comment
Up Next
Autoplay
-
03:25
Nokia Performance Results for 5G Packet Core with 2nd Gen AMD EPYC Processor
-
00:57
Design with Real-Time Rendering, Deliver Real-Time Results
-
01:25
Research at NVIDIA: AI Can Now Fix Your Grainy Photos by Only Looking at Grainy Photos
-
01:40
NVIDIA Studio | Create Realistic Materials in Substance Alchemist Faster With RTX
-
01:55
Trail Blazing our Future with AI and NVIDIA Research
-
01:50
NVIDIA RTX Brings Interactive Ray Tracing and Realistic Visualizations to KeyShot 9
-
01:20
NVIDIA Graphics Research
-
02:12
Visualizing Simulation Results with NVIDIA CloudXR and RTX GPUs
-
12:07
GTC 2016: Achieving Superhuman Results with AI (part 5)
-
02:17
Scan Objects into Realistic 3D Models with HP Z and NVIDIA GPUs
-
01:31
Interactive Visualization of High-Resolution, Global-Scale Climate Data in the Cloud
-
02:20
Generating Potential Accident Scenarios for Autonomous Vehicles Using AI - NVIDIA DRIVE Labs Ep. 27
-
00:34
NVIDIA GTC 2023 Keynote Teaser
-
02:13
Experience Hospitality Design on CloudXR with AWS
-
1:17:52
GTC 2023 Keynote with NVIDIA CEO Jensen Huang
-
02:48
BMW Group Celebrates Opening the World's First Virtual Factory in NVIDIA Omniverse
-
02:31
NVIDIA Omniverse Foundational Technology Montage I GTC Spring 2023 Edition
-
02:03
Amazon Robotics Deploys First Fully Autonomous Robot With NVIDIA Isaac Sim
-
02:04
Easily Scale and Unify Industrial Digitalization With NVIDIA Omniverse Cloud
-
03:14
I AM AI | NVIDIA GTC 2023 | Official Keynote Intro