Philipp Krähenbühl

Department of Computer Science
University of Texas at Austin
2317 Speedway
Austin, TX 78712-1757

email: philkr (at)
CV, DBLP, Google Scholar, github


I am an Assistant Professor in the Department of Computer Science at the University of Texas at Austin. I received my PhD in 2014 from the CS Department at Stanford University and then spent two wonderful years as a PostDoc at UC Berkeley.

My research interests lie in Computer Vision, Machine learning and Computer Graphics. I’m particularly interested in deep learning, as well as image segmentation and understanding.


Sampling Matters in Deep Embedding Learning
Chao-Yuan Wu, R. Manmatha, Alexander J. Smola and Philipp Krähenbühl
ICCV 2017
[pdf] [details]
Adversarial Feature Learning
Jeff Donahue, Philipp Krähenbühl and Trevor Darrell
ICLR 2017
[pdf] [details] [code]
Generative Visual Manipulationon the Natural Image Manifold
Jun-Yan Zhu, Philipp Krähenbühl, Eli Shechtman, and Alexei A. Efros
ECCV 2016
[pdf] [details] [project] [code]
Context Encoders: Feature Learning by Inpainting
Deepak Pathak, Philipp Krähenbühl, Jeff Donahue, Trevor Darrell and Alyosha Efros
CVPR 2016
[pdf] [details] [project] [code]
Learning Dense Correspondence via 3D-guided Cycle Consistency
Tinghui Zhou, Philipp Krähenbühl, Mathieu Aubry, Qixing Huang and Alyosha Efros
CVPR 2016
[pdf] [details] [project]
Data-dependent initializations of convolutional neural networks
Philipp Krähenbühl, Carl Doersch, Jeff Donahue and Trevor Darrell
ICLR 2016
[pdf] [details] [code] [py-faster-rcnn training scripts]
Learning a Discriminative Model for the Perception of Realism in Composite Images
Jun-Yan Zhu, Philipp Krähenbühl, Eli Shechtman and Alyosha Efros
ICCV 2015
[pdf] [details] [slides] [code]
Learning Data-driven Reflectance Priors for Intrinsic Image Decomposition
Tinghui Zhou, Philipp Krähenbühl and Alyosha Efros
ICCV 2015
[pdf] [details] [slides] [code]
Constrained Convolutional Neural Networks for Weakly Supervised Segmentation
Deepak Pathak, Philipp Krähenbühl and Trevor Darrell
ICCV 2015
[pdf] [details] [supplement] [slides] [code]
Learning to propose objects
Philipp Krähenbühl and Vladlen Koltun
CVPR 2015
[pdf] [details] [code]
Geodesic Object Proposals
Philipp Krähenbühl and Vladlen Koltun
ECCV 2014 (oral)
[pdf] [details] [slides] [poster] [code] [data]
Parameter Learning and Convergent Inference for Dense Random Fields
Philipp Krähenbühl and Vladlen Koltun
ICML 2013
[pdf] [details] [project] [code]
Efficient Nonlocal regularization for Optical Flow
Philipp Krähenbühl and Vladlen Koltun
ECCV 2012
[pdf] [details]
Saliency Filters: Contrast Based Filtering for Salient Region Detection
Federico Perazzi, Philipp Krähenbühl, Yael Pritch and Alexander Hornung
CVPR 2012
[pdf] [details] [project] [code]
Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
Philipp Krähenbühl and Vladlen Koltun
NIPS 2011 (best student paper)
[pdf] [details] [project] [code]
Gesture Controllers
Sergey Levine, Philipp Krähenbühl, Sebastian Thrun, Vladlen Koltun
[pdf] [details]
Retargeting of Streaming Video
Philipp Krähenbühl, Manuel Lang, Alexander Hornung and Markus Gross
SIGGRAPH Asia 2009
[pdf] [details]


Joining my research group

UT CS or ECE students: I’d recomment you to take my graduate deep learning class (CS395T), and start working with me throught that class.

Prospective students: Please read about our graduate admissions process and state your interested in my research group in your statement of purpose. Please do not contact me directly. The statistics are not in your favor either. We have not yet admitted a single student to UTCS who contacted me directly.

About my last name

I’m well aware that my last name is not the easiest one to write or cite (and I saw it butchered a bunch of times over the years). So to make things easier just pick your document type below and copy the string:

Regular text


Latex & Bibtex




If all the above fail, just use Kraehenbuehl.