Matthew Trentacoste

Now

I work on Generative AI at Meta, where I spend a lot of time thinking about training data.

When I'm not doing that, I'm usually trying to get lost in the wilderness. I camp, hike, find things to drive over, and spend a fair amount of time getting to out of the way places to photograph them.

Get in touch via email (my initials at this domain) or Twitter.

Previous eras

At Figma and Sprig, I found myself in a variety of data science roles from 2014-2017.

At Adobe and Pocket Pixels, I worked on a number of projects in the early days of mobile photography from 2011-2014.

At Dolby and BrightSide, prior to their acquisition, I worked on high dynamic range displays from 2004-2009.

My Ph.D. is in image processing and human visual perception at University of British Columbia, from 2003-2012.

Random artifacts

2024
Meta GenAI image and video tools for advertisers
2022
Recreation.gov checker
2017
iBooks Highlights
2016
California WaterBot
2015
Adobe Photoshop Fix
2014
Recognizing Image Style
2013
Image Features in Python (talk) (slides)
2012
Scale-Dependent Perception of Countershading: Enhancement or Artifact?
Color Splash
2011
Manipulating Scale-Dependent Perception of Images (Ph.D.)
Glare Encoding of High Dynamic Range Images
Blur-Aware Image Downsizing
2010
Defocus Techniques for Camera Dynamic Range Expansion
2009
Dolby Vision display
2007
Photometric Image Processing for High Dynamic Range Displays
Ldr2Hdr: On-the-fly Reverse Tone Mapping of Legacy Video and Photographs
2006
Photometric Image Processing for High Dynamic Range Displays (M.Sc.)
2005
High Dynamic Range Techniques in Graphics: from Acquisition to Display
Real Illumination from Virtual Environments (video)
Volume Rendering for High Dynamic Range Displays
2004
High Dynamic Range Display Systems
2003
Implementing Performance Numerical Libraries on Graphics Hardware (B.Sc.)

What information consumes is rather obvious: it consumes the attention of its recipients. Hence a wealth of information creates a poverty of attention and a need to allocate that attention efficiently among the overabundance of information...