• Google Scholar
  • LinkedIn Social Icon
  • Twitter Social Icon

Brian Price

Principal Scientist
Adobe Research


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

ECCV 2022

Oct 25, 2022

It's ECCV this week. I have one paper, One-Triamp Video Matting. I also had an oral paper at the TiE: Text in Everything workshop. Check them out on my Papers page.


Jun 20, 2022

I have two papers at CVPR this year. Check them out at my Papers page.

Adobe named Innovative Company for 2022

Mar 9, 2022

Adobe was recognized as one of the top ten most innovative companies in AI for 2022 by Fast Company.

Recent Publications

One-Trimap Video Matting

Hongje Seong, Seoung Wug Oh, Brian Price, Euntai Kim, Joon-Young Lee

ECCV 2022

End-to-end Document Recognition and Understanding with Dessurt

Brian Davis, Bryan Morse, Chris Tensmeyer, Brian Price, Curtis Wigington, Vlad Morariu

TiE: Text in Everything (ECCV 2022 Workshop)


Generalizing Interactive Backpropagating Refinement for Dense Prediction Networks

Fanqing Lin, Brian Price, Tony Martinez

CVPR 2022


Recent Patents

Neural Networks For Multi-label Classification Of Sequential Data

Curtis Wigington, Brian Price, Scott Cohen

US Patent 11,468,298. Oct 11, 2022.

Removing and Replacing Objects in Images according to a Directed User Conversation

Scott Cohen, Brian Price, Abhinav Gupta

GB Patent 2569847. Sep 28, 2022.

Automatically Generating a Trimap Segmentation for a Digital Image by Utilizing a Trimap Generation Neural Network.

He Zhang, Seyed Morteza Safdarnejad, Yilin Wang, Zijun Wei, Jianming Zhang, Salil Tambe, Brian Price.

US Patent 11,393,100. Jul 19, 2022.

Technologies Highlights

Object-aware Refine Edge

A few years back I helped to advise on the creation of the Select and Mask workspace in Photoshop that allows users to select objects in images.  Photoshop added a new mode that allows for improved extraction of hair for complex images.  This mode is a follow on to our Deep Image Matting paper from CVPR 2017.