David Fouhey

After 5 wonderful and busy years at CMU, I have moved to UC Berkeley. Please find my new personal website here if you are not automatically redirected in 5 seconds.

David Fouhey

Quick info: CV Google Scholar Semantic Scholar
Email (Reveal):
If you're the type of person who browses without javascript, your first guess for my email is probably going to be right.
Name FAQ: `Foe'-`eee'. It rhymes with snowy or Joey: the key is to forget how it is spelled. It (but not me) is from the County Cork, Ireland.
Pictures: One picture is hard to identify a person with. Here are some more.

Executive summary: I am a postdoctoral fellow (2016-) at UC Berkeley, working with Jitendra Malik and Alyosha Efros. I received a Ph.D. in Robotics (2011-2016) from The Robotics Institute at Carnegie Mellon University, where I worked with Abhinav Gupta and Martial Hebert and was a NSF and then NDSEG fellow.

News

News

I started a postdoc in Fall 2016 at UC Berkeley with Jitendra Malik and Alyosha Efros.
My picks for CVPR 2016 were featured in CVPR Daily News
I co-taught 16-824 (Visual Learning and Recognition) in Spring 2016.
I visited the VGG group at Oxford for Summer 2015.

Research

I work on computer vision and machine learning. I am interested in getting computers to understand the world in terms of:

physical properties: how do we recover intrinsically 3D properties from a 2D image? which 3D properties should we perceive and how do they interact? and how do we reconcile our strong prior knowledge about this problem with data-driven techniques?
functional properties: how do we understand how an agent (e.g., human or robot) can interact with the world? and what are the implications for 3D understanding?

as well as how these two relate to semantics, or a language-based understanding.

Teaching

CMU 16-824 (Visual Learning and Recognition), Spring 2016. Co-taught with Abhinav Gupta.
Tutorial on 3D Scene Understanding at ECCV 2014 with Abhinav Gupta, Martial Hebert, and Derek Hoiem.

Publications

R. Girdhar, D. Fouhey, M. Rodriguez, A. Gupta
Learning a Predictable and Generative Vector Representation for Objects
To appear at ECCV 2016 (Spotlight)
[Publication (PDF)] [Bibtex]
[Project Page]

Factoring Scenes into 3D Structure and Style
D. Fouhey
Doctoral Dissertation
[Dissertation (PDF)] [Bibtex]
[Defense Slides (PDF)]

D. Fouhey, A. Gupta, A. Zisserman
3D Shape Attributes
In CVPR 2016 (Oral - Watch the presentation on Youtube)
[Publication (PDF)] [Bibtex]
[Project Page] [Poster (PDF)] [Talk (PPTX)] [Talk (PDF)]

R. Girdhar, D. Fouhey, K. M. Kitani, A. Gupta, M. Hebert
Cutting through the Clutter: Task-Relevant Features for Image Matching
In WACV 2016.
[Publication (PDF)] [Bibtex]

D. Fouhey, W. Hussain, A. Gupta, M. Hebert
Single Image 3D Without a Single 3D Image
In ICCV 2015.
[Publication (PDF)] [Bibtex]
[Poster (PDF)] [Supplemental (PDF)] [Bonus Details (PDF)]

X. Wang, D. Fouhey, A. Gupta
Designing Deep Networks for Surface Normal Estimation
In CVPR 2015.
[Publication (PDF)] [Bibtex]

D. Fouhey, A. Gupta, and M. Hebert
Unfolding an Indoor Origami World
In ECCV 2014 (Oral - Watch the presentation on VideoLectures.net )
[Publication (PDF)] [Bibtex]
[Project Page] [Extended Results (PDF)]

D. Fouhey and C.L. Zitnick
Predicting Object Dynamics in Scenes
In CVPR 2014.
[Publication (PDF)] [Bibtex]
[Project Page] [Supplemental (PDF)]

D. Fouhey, V. Delaitre, A. Gupta, A. Efros, I. Laptev, and J. Sivic.
People Watching: Human Actions as a Cue for Single View Geometry.
Accepted in IJCV (extended version of ECCV 2012 paper).
[Preprint (PDF)] [Final version (via Springer)]

D. Fouhey, A. Gupta, and M. Hebert
Data-Driven 3D Primitives for Single Image Understanding
In ICCV 2013.
[Publication (PDF)] [Bibtex]
[Project Page] [Poster (PDF)]

D. Fouhey, V. Delaitre, A. Gupta, A. Efros, I. Laptev, and J. Sivic.
People Watching: Human Actions as a Cue for Single View Geometry.
In ECCV 2012 (Oral - Watch the presentation on VideoLectures.net ).
[Publication (PDF)] [Bibtex]
[Project Page]

V. Delaitre, D. Fouhey, I. Laptev, J. Sivic, A. Gupta, and A. Efros.
Scene Semantics from Long-term Observation of People.
In ECCV 2012.
[Publication (PDF)] [Bibtex]
[Project Page]

D. Fouhey, A. Collet, M. Hebert, and S. Srinivasa
Object Recognition Robust to Imperfect Depth Data.
In CDC4CV 2012 in conjunction with ECCV 2012.
[Publication (PDF)] [Bibtex]
[Supplemental(PDF)] [Supp. Video 1] [Supp. Video 2]

M. Costanza-Robinson, B. Estabrook, and D. Fouhey
Representative elementary volume estimation for porosity, moisture saturation, and air-water interfacial areas in unsaturated porous media: Data quality implications
(Sorry for not posting a pre-print!)
In Water Resources Research, Volume 47, 2011.
[Official Version] [Bibtex]

D. Fouhey, D. Scharstein, and A. Briggs.
Multiple plane detection in image pairs using J-linkage.
In ICPR 2010.
[Publication (PDF)] [Bibtex]
Implementation (Python and C) [Code (Zip)] [Poster (PDF)]

Miscellaneous

You may be interested in the following.

Writing (arranged in chronological order):

My Ph.D. dissertation, Factoring Scenes into 3D Structure and Style (Dissertation and Defense Slides)
A note on some practical considerations when evaluating surface normals
My A.B. thesis, Multi-Model Estimation in the Presence of Outliers (Thesis and Poster and Presentation)

Miscellaneous

CMU RI Thesis Template (zip) based off of a CMU RI tech report template from Daniel Morris.

Fun & Games

Academic Ancestry and Erdös Number: See where I fit in!
#1 Messiest Desk: My desk was voted #1 messiest desk in the second floor of Smith Hall at Carnegie Mellon during the RI's open house for 2016.
If a cluttered desk is an indication of a cluttered mind, then what does an empty desk indicate?
Deep Excel: Daniel Maturana and I released ExcelNet, a break-through technology that merges the power of Deep Learning with Excel.
The spreadsheet The whitepaper The pitch slides Protips (actually quite helpful)
Visual Rank Estimation: Visually Identifying Rank with Daniel Maturana proves that linear algebra can be replaced with machine learning. It also shows that if you are a CNN, the much-hated jet colormap is actually the best colormap. Winner of the ``Most Frighteningly Like Real Research'' award at SIGBOVIK 2016.
Celebrity Learning: You may also know my award-winning work with Daniel Maturana on celebrity-themed learning, making money at home from Hilbert's Nulstellensatz, and more from OneWeirdKernelTrick.com
Award-Winning Optimization Sheet: I wrote an award-winning one page cheat-sheet for Convex Optimization at CMU (10-725). Be sure to check the watermark!