skip to main content
Derek W Hoiem
Derek W Hoiem

Derek W Hoiem

Associate Professor
  • Computer Science
(217) 333-0806
3312 Siebel Center for Comp Sci

For more information

Biography

Derek Hoiem is an associate professor in Computer Science. One of the main research directions is recovering 3D geometry from single images and improving spatial understanding of scenes. For example, Hoiem produced the first algorithm to generate 3D models from single photos of typical outdoor scenes, and his group contributed foundational works in 3D scene modeling from RGB and RGBD images. Other important directions include learning object representations, for example work on attribute-based representations, and improving our understanding of generalization and ability to extend learned representations to new tasks. Hoiem's educational background includes undergrad degrees in CS and EE from SUNY Buffalo, a PhD in Robotics from Carnegie Mellon, and a Beckman Postdoc Fellowship. Research awards include ACM Doctoral Dissertation Award honorable mention, CVPR best paper award, Intel Early Career Faculty award, Sloan Fellowship, and PAMI Significant Young Researcher award. Derek Hoiem is also co-founder and Chief Scientist of Reconstruct, which visually documents construction sites, matching images to plans and analyzing productivity and risk for delay.

Academic Positions

  • Associate Professor, Department of Computer Science, UIUC, 2015 to present.
  • Associate Professor (Affiliate), Department of Electrical and Computer Engineering, UIUC, 2015 to present.

Research Interests

  • Computer Vision, Object Recognition, Scene Understanding, Graphics

Selected Articles in Journals

  • C Zou, R Guo, Z Li, D Hoiem, "Complete 3D scene parsing from an RGBD image", International Journal of Computer Vision (IJCV), 127(2), Feb 2019.
  • Z. Li and D. Hoiem, “Learning without Forgetting”, IEEE Pattern Analysis and Machine Intelligence (PAMI), 99, Nov 2017.
  • R. Guo and D. Hoiem, "Labeling Complete Surfaces in Scene Understanding", International Journal of Computer Vision (IJCV), 112 (2), April 2015.
  • I. Endres and D. Hoiem, "Category-Independent Object Proposals with Diverse Ranking", IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 36 (2), 2014.
  • G. Wang, D. Forysth, and D. Hoiem, “Improved Object Categorization and Detection Using Comparative Object Similarity”, IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 35 (10), Oct 2013.
  • G. Wang, D. Hoiem, and D. Forsyth, “Learning image similarity from Flickr groups using fast kernel machines”, IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 16, Jan 2012.
  • R. Guo, Q. Dai, and D. Hoiem, " Paired Regions for Shadow Detection and Removal", IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), No 2, Oct 2012.
  • K. Karsch, V. Hedau, D. Forsyth, D. Hoiem, "Rendering Synthetic Objects into Legacy Photographs", ACM Transactions on Graphics (SIGGRAPH Asia), 2011.
  • D. Hoiem, A.A. Efros, and M. Hebert, “Recovering Occlusion Boundaries from an Image," International Journal of Computer Vision 91, No. 3, 2011.
  • T.L. Berg, A. Sorokin, G. Wang, D.A. Forsyth, D. Hoiem, A. Farhadi, and I. Endres, "It's All About the Data", Proc. IEEE Special Issue on Internet Vision, August 2010, 98 (8), 1434-1453. (citations:4).
  • D. Hoiem, A.A. Efros, and M. Hebert, "Putting Objects in Perspective,"International Journal of Computer Vision, Oct 2008. Invited paper
  • D. Hoiem, A.A. Efros, and M. Hebert, "Recovering Surface Layout from an Image," International Journal of Computer Vision, Vol. 75, No. 1, October 2007.
  • J-F. Lalonde, D. Hoiem, A.A. Efros, J. Winn, C. Rother and A. Criminisi, "Photo Clip Art," ACM Transactions on Graphics (SIGGRAPH), 2007.
  • D. Hoiem, A.A. Efros, and M. Hebert, "Automatic Photo Pop-up," ACM Transactions on Graphics (SIGGRAPH proc.), 2005.

Articles in Conference Proceedings

  • T Gupta, D Schwenk, A Farhadi, D Hoiem, A Kembhavi, "Imagine this! scripts to compositions to videos", Proceedings of the European Conference on Computer Vision (ECCV), 598-613, 2018.
  • J DeGol, T Bretl, D Hoiem, "Improved structure from motion using fiducial marker matching", Proceedings of the European Conference on Computer Vision (ECCV), 273-288, 2018.
  • J Degol, JY Lee, R Kataria, D Yuan, T Bretl, D Hoiem, "Feats: Synthetic feature tracks for structure from motion evaluation", International Conference on 3D Vision (3DV), 352-361, 2018.
  • D. Shin, C. Fowlkes, D. Hoiem, "Pixels, voxels, and views: A study of shape representations for single view 3D object shape prediction," CVPR 2018, Salt Lake City, UT, 2018.
  • C. Zou, A. Colburn, Q. Shan, D. Hoiem, "LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image," CVPR 2018, Salt Lake City, UT, 2018.
  • T. Gupta, K. Shih, S. Singh, D. Hoiem, "Aligned Image-Word Representations Improve Inductive Transfer Across Vision-Language Tasks," ICCV 2017, Venice, Italy, 2017
  • J. DeGol, T. Bretl, D. Hoiem, "ChromaTag: A Colored Marker and Fast Detection Algorithm," ICCV 2017, Venice, Italy. 2017
  • C. Zou, E. Yumer, J. Yang, D. Ceylan, D. Hoiem, "3D-PRNN: Generating Shape Primitives with Recurrent Neural Networks," ICCV 2017, Venice, Italy. 2017
  • S. Singh, D. Hoiem, and D. Forsyth, “Swapout: Learning an ensemble of deep architectures”, Neural Information Processing Systems (NIPS)), 2016.
  • Z. Li and D. Hoiem, “Learning without Forgetting”, European Conference on Computer Vision (ECCV)), 2016.
  • S. Singh, D. Hoiem, and D. Forsyth, “Learning to Localize Little Landmarks”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR)), 2016.
  • J. DeGol, M. Golparvar-Fard, and D. Hoiem, “Geometry-Informed Material Recognition”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR)), 2016.
  • K.J. Shih, S. Singh, and D. Hoiem, “Where to Look: Focus Regions for Visual Question Answering”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR)), 2016.
  • K.J. Shih, A. Mallya, S. Singh, D. Hoiem, "Part Localization using Multi-Proposal Consensus for Fine-Grained Categorization", British Conference on Machine Vision (BMVC), 2015.
  • S. Singh, D. Hoiem and D.A. Forsyth, "Learning to Find Landmarks", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
  • J. Rock, T. Gupta, J. Gwak, D. Shin, and D. Hoiem, "Completing 3D Object Shape from One Depth Image", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
  • Q. Dai, P. Carr, L. Sigal, and D. Hoiem, "Family Member Identification from Photo Collections", IEEE Winter Conference on Applications in Computer Vision (WACV), 2015.
  • R. Guo and D. Hoiem , “Support Surface Prediction in Indoor Scenes”, International Conference on Computer Vision (ICCV), 2013.
  • K. Karsch, Z. Liao, J. Rock, J.T. Barron, and D. Hoiem , “Boundary Cues for 3D Object Shape Recovery”, Computer Vision and Pattern Recognition (CVPR), 2013.
  • I. Endres, K. Shih, J. Jiaa, and D. Hoiem, “Learning Collections of Part Models for Object Recognition”, Computer Vision and Pattern Recognition (CVPR), 2013.
  • D. Hoiem, Y. Chodpathumwan, and Q. Dai, “Diagnosing Error in Object Detectors”, European Conference on Computer Vision (ECCV), 2012. Acceptance rate, oral: 4%
  • R. Guo and D. Hoiem, “Beyond the line of sight: labeling the underlying surfaces”, European Conference on Computer Vision (ECCV), 2012. Acceptance rate, oral: 4%
  • N. Silberman, D. Hoiem, P. Kohli, and R. Fergus, “Indoor Segmentation and Support Inference from RGBD Images”, European Conference on Computer Vision (ECCV), 2012. Acceptance rate, oral: 4%
  • Ian Endres, Vivek Srikumar, Ming-wei Chang, and Derek Hoiem, “Learning Shared Body Plans”, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2012. Acceptance rate, poster: 24%
  • Qieyun Dai and Derek Hoiem, “Learning to Localize Detected Objects”, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2012. Acceptance rate, poster: 24%
  • Varsha Hedau, Derek Hoiem, and David Forsyth, “Recovering Free Space of Indoor Scenes from a Single Image”, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2012. Acceptance rate, poster: 24%
  • M. Dikmen, D. Hoiem, and T.S. Huang, “A Data-driven Method for Feature Transformation”, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), 2012. Acceptance rate, poster: 24%
  • R. Guo, Q. Dai, and D. Hoiem, “Single-Image Shadow Detection and Removal using Paired Regions”, Computer Vision and Pattern Recognition 2011. Acceptance rate, oral: 3.5%
  • I. Endres and D. Hoiem, “Category Independent Object Proposals”, European Conference on Computer Vision 2010. Acceptance rate, poster: 27%
  • V. Hedau, D. Hoiem, and D.A. Forsyth, “Thinking Inside the Box: Using Appearance Models and Context Based on Room Geometry”, European Conference on Computer Vision 2010. Acceptance rate, poster: 27%
  • A. Farhadi, I. Endres, and D. Hoiem, “Attribute-Centric Recognition for Cross-Category Generalization”, IEEE Conference on Computer Vision and Pattern Recognition 2010. Acceptance rate, poster: 22.3%
  • I. Endres, A. Farhadi, D. Hoiem, and D.A. Forsyth, “The Benefits and Challenges of Collecting Richer Object Annotations”, Advancing Computer Vision with Humans in the Loop (CVPR workshop) 2010.
  • G. Wang, D.A. Forsyth, and D. Hoiem, “Comparative object similarity for improved recognition with few or no examples”, IEEE Conference on Computer Vision and Pattern Recognition 2010. Acceptance rate, poster: 22.3%
  • G. Wang, D. Hoiem, and D.A. Forsyth, "Learning Image Similarity from Flickr Groups Using Stochastic Intersection Kernel Machines", International Conference on Computer Vision 2009. Acceptance rate, poster: 23%
  • V. Hedau, D. Hoiem, and D.A. Forsyth, "Recovering the Spatial Layout of Cluttered Rooms", International Conference on Computer Vision 2009. Acceptance rate, poster: 23%
  • S.K. Divvala, D. Hoiem, J.H. Hays, A.A. Efros, and M. Hebert, "An Empirical Study of Context in Object Detection", IEEE Conference on Computer Vision and Pattern Recognition 2009. Acceptance rate, poster: 26%
  • G. Wang, D. Hoiem, and D.A. Forsyth, "Building Text Features for Object Image Classification", IEEE Conference on Computer Vision and Pattern Recognition 2009. Acceptance rate, poster: 26%
  • A. Farhadi, I. Endres, D. Hoiem, and D.A. Forsyth, "Describing Objects by their Attributes", IEEE Conference on Computer Vision and Pattern Recognition 2009. Acceptance rate, poster: 26%
  • M. Szummer, P. Kohli, and D. Hoiem, "Learning CRFs using Graph Cuts," European Conference on Computer Vision 2008. Acceptance rate, poster: 23%
  • D. Hoiem, A.A. Efros, and M. Hebert, "Closing the Loop on Scene Interpretation," IEEE Conference on Computer Vision and Pattern Recognition 2008. Acceptance rate, oral: 4%
  • D. Hoiem, C. Rother, and J. Winn, "3D LayoutCRF for Multi-View Object Class Recognition and Segmentation," IEEE Conference on Computer Vision and Pattern Recognition 2007. Acceptance rate, poster: 23%
  • A.N. Stein, D. Hoiem, and M. Hebert, "Learning to Extract Object Boundaries using Motion Cues," International Conference on Computer Vision 2007. Acceptance rate, oral: 4%
  • D. Hoiem, A.N. Stein, A.A. Efros, and M. Hebert, "Recovering Occlusion Boundaries from a Single Image," International Conference on Computer Vision 2007. Acceptance rate, oral: 4%
  • D. Hoiem, A.A. Efros, and M. Hebert, "Putting Objects in Perspective," IEEE Conference on Computer Vision and Pattern Recognition 2006. Acceptance rate, oral: 4.8%; best paper out of 1131 submitted
  • B. Nabbe, D. Hoiem, A.A. Efros, and M. Hebert, "Opportunistic use of vision to push back the path-planning horizon," IROS 2006. Acceptance rate: 46%
  • Y. Ke, D. Hoiem, and R. Sukthankar, "Computer Vision for Music Identification," IEEE Conference on Computer Vision and Pattern Recognition, 2005. Acceptance rate, poster: 22%
  • D. Hoiem, A.A. Efros, and M. Hebert, "Geometric Context from a Single Image," International Conference on Computer Vision 2005. Acceptance rate, poster: 16%
  • D. Hoiem, Y. Ke, and R. Sukthankar, "SOLAR: Sound Object Localization and Retrieval in Complex Audio Environments," International Conference on Acoustics, Speech and Signal Processing, 2005.
  • L. Huston, R. Sukthankar, D. Hoiem, and J. Zhang, "SnapFind: Brute Force Interactive Image Retrieval," International Conference on Image and Graphics, 2004.
  • D. Hoiem, R. Sukthankar, H. Schneiderman, and L. Huston, "Object-Based Image Retrieval Using the Statistics of Images," IEEE Conference on Computer Vision and Pattern Recognition, 2004. Acceptance rate, poster: 23.6%

Honors

  • IEEE PAMI Young Researcher Award (2014)
  • Dean's Award for Excellence in Research (2014)
  • Sloan Research Fellowship (2013)
  • NSF CAREER Award (2011)

Teaching Honors

  • List of Teachers Ranked as Excellent (Fall 2017)
  • List of Teachers Ranked as Excellent (Spring 2017)
  • List of Teachers Ranked as Excellent (Spring 2015)
  • List of Teachers Ranked as Excellent (Fall 2014)
  • List of Teachers Rated Excellent (Fall 2013)
  • List of Teachers Rated Excellent (Spring 2012)
  • List of Teachers Rated Excellent (Fall 2011)
  • List of Teachers Rated Excellent (Spring 2011)
  • List of Teachers Rated Excellent (Fall 2010)

Research Honors

  • Campus Distinguished Promotion Award (2015)
  • Best Paper Award: IEEE Winter Conference on Applications in Computer Vision (WACV)(2015)
  • IEEE PAMI Young Researcher Award (2014)
  • CW Gear Junior Faculty Award (2014)
  • Dean's Award for Excellence in Research (2014)
  • Sloan Research Fellowship (2013)
  • Intel Early Career Faculty Honor Program Award (2012)
  • NSF CAREER Award (2011)
  • Microsoft New Faculty Fellowship Finalist (2010, 2011)
  • ACM Doctoral Dissertation Award, Honorable Mention, 2008. (runner-up for best dissertation in computer science, internationally)
  • Carnegie Mellon University SCS Distinguished Dissertation Award, 2008 (best dissertation in computer science at CMU)
  • Best Paper Award: IEEE Computer Vision and Pattern Recognition (CVPR) (2006)

Courses Taught

  • CS 445 - Computational Photography
  • CS 543 - Computer Vision
  • ECE 549 - Computer Vision