Brian Price
Principal Scientist
Adobe Research
Email:
As a research scientist at Adobe, I research Computer Vision, develop new technologies, transfer them to Adobe products, and work with universities and PhD students through collaborations and internships. (See full bio here)
Research Interests: Computer Vision, Graphics, and Machine Learning, especially segmentation (interactive object selection, matting, panoptic/semantic segmentation, video segmentation), image synthesis, and document understanding.
Latest News
Adobe MAX week
​
This week is Adobe MAX. A lot of new Adobe product features will be released this week, including several that I contributed to such as the Object-aware Refine Edge mode.
BMVC
​
It is BMVC this week. I have one paper on "Text and Style Conditioned GAN for Generation of Offline Handwriting Lines." Head to my Papers to check it out.
ECCV week
​
I am attending ECCV (remotely) this week. Our paper "PhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and Click" is a spotlight.
Text and Style Conditioned GAN for Generation of Offline Handwriting Lines
Brian Davis, Chris Tensmeyer, Brian Price, Curtis Wigington, Bryan Morse, Rajiv Jain
PhraseClick: Toward Achieving Flexible Interactive Segmentation by Phrase and Click
Henghui Ding, Scott Cohen, Brian Price, and Xudong Jiang
Interactive Training and Architecture for Deep Object Selection
Marco Forte, Brian Price, Scott Cohen, Ning Xu, Francois Pitie
ICME 2020 (Best Paper runner up)
Table Layout Determination Using A Machine Learning System
Brian Price, Vlad Morariu, Scott Cohen, Christopher Tensmeyer
US Patent 10,846,524. Nov. 24, 2020.
Image Object Segmentation Based on Temporal Information
Ning Xu, Brian Price, Scott Cohen
US Patent 10,818,014. Oct 27, 2020.
Generating Object Selections on a Live Camera Feed
CN Patent ZL2015104235674. Sep. 11, 2020.
Technologies Highlights
Select Subject for Portraits
Photoshop shipped a new version of Select Subject that automatically segments people in images. It is able to get fine detail like hair. Some of the technology that I have developed regarding selecting hair detail is part of this new feature.
