Leveraging Deep Learning to Fix Images
Deep Fill makes editing a photo easier using a form of deep learning known as Generative Adversarial Networks (GANs) to train an innovative system. The tool enables users to remove undesirable objects from an image by letting Deep Fill do the work.
February 8, 2018
Whose Likes Matter Most? Ask this Learning Algorithm
Now, new work from Adobe Research offers a promising means to empower computers to find online influencers on their own—using sophisticated methods in machine learning.
January 24, 2018
Search for Great Moments in Videos with Natural Language
We all have long, mostly dull home videos in our memory cards that contain just a few great moments. What if we could train computers to find specific scenes?
January 18, 2018
Stitch Together a Perfect Scene with Experimental Tool
Scene Stitch gives creatives the chance to re-imagine an image and to easily explore a range of possibilities to change it.
January 9, 2018
Add Depth to VR Video with Sidewinder
Is there a low-cost, easy-capture way to improve the realism of VR video? Adobe Research has found a promising path with Sidewinder.
December 14, 2017
Cloak: Remove Unwanted Objects in Video
By Meredith Alexander Kunz, Adobe Research Project Cloak, an experimental tool by Adobe Research, offers an innovative way to remove unwanted objects from a video. Object removal is a huge pain point for visual effects artists, who currently spend countless hours manually erasing boom-microphones, special
December 11, 2017
CareersResearcher Spotlights
Researcher Spotlight: Eunyee Koh
Eunyee Koh, senior research scientist at Adobe Research, focuses on machine learning algorithms and computer-human interaction. She’s been with the group since 2008 and leads her own team.
December 4, 2017
Adobe Research Publishes 66 Papers at Top Visual Computing Conferences in 2017
This year, Adobe Research continued in its core mission of developing innovative new technologies, publishing 66 research papers at top computer vision and computer graphics conferences.
November 28, 2017
From Blurry to Crisp: Video Super Resolution Enhances It All
What was once science fiction is now one step closer to reality with the work of Adobe Research’s Zhaowen Wang and collaborators.
November 15, 2017
With Scribbler, Color Your World
Adobe Research scientists have taken on the problem of how to generate realistic imagery using deep convolutional networks. The result: Project Scribbler.
November 15, 2017
Need New Toys? Tool Lets You Build Your Own 3D Mechanical Creations
A novel technology co-created by Adobe Research allows designers to automatically adapt a working mechanism to fit a wide range of 3D objects, creating millions of opportunities for imaginative toys and functional shapes.
November 3, 2017