Kostas Daniilidis
Ruth Yalom Stone Professor


GRASP Laboratory
Department of Computer and Information Science
School of Engineering and Applied Science
University of Pennsylvania

News: 4th Workshop Geometry Meets Deep Learning at ICCV 2019
Our EVflownet Self-supervised optical flow estimation for event-based cameras paper was Best Student paper finalist at RSS'18.
Our team was one of the five finalists at the KUKA Innovation Competition demonstrating Automatic Precise Liquid Dispensing.
Our paper Probabilistic Data Association for Semantic SLAM won the Best Conference Paper Award at ICRA 2017 ! A sneak peek here, more material, and the ceremony.

The worldwide first Micromasters in Robotics taught by GRASP faculty!

My robohub podcast on geometry, robots, deep learning, start-ups, and PhD.


Recent Papers: My publications in Google Scholar sorted by citation or by year, and in DBLP and my CV.

2019

Nikos Kolotouros, Georgios Pavlakos, Kostas Daniilidis, Convolutional Mesh Regression for Single-Image Human Shape Reconstruction, IEEE CVPR 2019 (oral), pdf,

Alex Zhu, Liangzhe Yuan, Kenneth Chaney, Kostas Daniilidis, Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion, IEEE CVPR 2019, pdf

Rybkin, Oleh; Pertsch, Karl; Derpanis, Konstantinos G; Daniilidis, Kostas; Jaegle, Andrew; ",Learning what you can do before doing anything, ICLR 2018, pdf.

Monroe Kennedy III, Karl Schmeckpeper, Dinesh Thakur,R Chenfanfu Jiang, Vijay Kumar and Kostas Daniilidis, Autonomous Precision Pouring from Unknown Containers, to be submitted to IEEE Robotics and Automation Letters. pdf

Zhu, Alex Zihao; Liu, Wenxin; Wang, Ziyun; Kumar, Vijay; Daniilidis, Kostas; ",Robustness meets deep learning: An end-to-end hybrid pipeline for unsupervised learning of egomotion,arXiv preprint arXiv:1812.08351,2018,

Phillips, Stephen; Daniilidis, Kostas; ",All Graphs Lead to Rome: Learning Geometric and Cycle-Consistent Representations with Graph Convolutional Networks,arXiv preprint arXiv:1901.02078,2019,

Zhu, Alex Zihao; Wang, Ziyun; Daniilidis, Kostas; ",Motion Equivariant Networks for Event Cameras with the Temporal Normalization Transform,arXiv preprint arXiv:1902.06820,2019,

Esteves, Carlos; Xu, Yinshuang; Allen-Blanchette, Christine; Daniilidis, Kostas; ",Equivariant Multi-View Networks,arXiv preprint arXiv:1904.00993,,,,2019,

2018

Alex Zihao Zhu, Liangzhe Yuan, Kenneth Chaney, and Kostas Daniilidis. EV-flownet: Self-supervised optical flow estimation for event-based cameras. In Robotics: Science and Systems , 2018. pdf

Carlos Esteves, Christine Allen-Blanchette, Xiaowei Zhou, and Kostas Daniilidis. Polar transformer networks. In Int. Conf. Learning Representations, 2018. pdf

Carlos Esteves, Kostas Daniilidis, Ameesh Makadia, and Christine Allec-Blanchette. Learning so(3) equivariant representations with spherical cnns. In Proceedings of the European Conference on Computer Vision (ECCV) , pages 52--68, 2018. pdf

Andrew Jaegle, Stephen Phillips, Daphne Ippolito, and Kostas Daniilidis. Understanding image motion with group representations. In International Conference on Learning Representations , 2018. pdf

Liu, Wenxin, Giuseppe Loianno, Kartik Mohta, Kostas Daniilidis, and Vijay Kumar. "Semi-Dense Visual-Inertial Odometry and Mapping for Quadrotors with SWAP Constraints." In 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 1-6. IEEE, 2018. pdf

Kartik Mohta, Michael Watterson, Yash Mulgaonkar, Sikang Liu, Chao Qu, Anurag Makineni, Kelsey Saulnier, Ke~Sun, Alex Zhu, Jeffrey Delmerico, et~al. Fast, autonomous flight in gps-denied and cluttered environments (vol 35, pg 101, 2018). JOURNAL OF FIELD ROBOTICS , 35(3):417--417, 2018. pdf

Georgios Pavlakos, Xiaowei Zhou, and Kostas Daniilidis. Ordinal depth supervision for 3d human pose estimation. In IEEE Comp. Vis. Pattern Recog. (CVPR) , 2018. pdf

Georgios Pavlakos, Luyang Zhu, Xiaowei Zhou, and Kostas Daniilidis. Learning to estimate 3d human pose and shape from a single color image. In IEEE Comp. Vis. Pattern Recog. (CVPR) , 2018. pdf

Qianqian Wang, Xiaowei Zhou, and Kostas Daniilidis. Multi-image semantic matching by mining consistent features. In IEEE Comp. Vision Pattern Recognition , 2018. pdf

Xiaowei Zhou, Sikang Liu, Georgios Pavlakos, Vijay Kumar, and Kostas Daniilidis. Human motion capture using a drone. In IEEE Int. Conf. Robotics and Automation , 2018. pdf

Xiaowei Zhou, Menglong Zhu, Georgios Pavlakos, Spyridon Leonardos, Konstantinos~G Derpanis, and Kostas Daniilidis. Monocap: Monocular human motion capture using a cnn coupled with a geometric prior. IEEE Transactions on Pattern Analysis and Machine Intelligence , 2018. pdf

Alex~Zihao Zhu, Yibo Chen, and Kostas Daniilidis. Realtime time synchronized event-based stereo. In European Conference on Computer Vision , 2018. pdf

Alex~Zihao Zhu, Dinesh Thakur, Tolga Ozaslan, Bernd Pfrommer, Vijay Kumar, and Kostas Daniilidis. The multi vehicle stereo event camera dataset: An event camera dataset for 3d perception. IEEE Robotics and Automation Letters , 3(3):2032--2039, 2018. pdf

PhD Students: Bernadette Bucher , Evangelos Chatzipantazis , Nikos Kolotouros , Oleh Rybkin , Kenneth Chaney, Kendall Queen , Wenxin Liu, Carlos Esteves, George Pavlakos , Alex Zhu, Stephen Phillips, Spyros Leonardos , Christine Allen-Blanchette , .

Postdocs: Marc Badger

Alumni PhDs: Monroe Kennedy III (co-advised with Vijay Kumar), Jason Owens (ARL), Mabel Zhang (OSRF), Drew Jaegle (Deepmind), Cody Phillips (AVVIR), Nikolay Atanasov (UC San Diego, co-advised with George Pappas), Menglong Zhu (Google), Mayank Bansal (Google Waymo), Roy Anati (Google). Alexander Patterson IV (SightLogix) Oleg Naroditsky (Apple), Alexander Toshev (Google Brain), Ankita Kumar, (Oracle), Nima Moshtagh (JHU APL, co-advised with Ali Jadbababai). Ameesh Makadia (Google Research), Volkan Isler (U. of. Minnesota, coadvised with Sampath Kannan), Christopher Geyer (Berkshire Grey), Adnan Ansar (JPL/NASA), Weichuan Yu (HKUST).

Alumni Postdocs: Bernd Pfrommer Xiaowei Zhou (Zhejiang University), Roberto Tron (Boston University), Luis Puig (Geomagical), Konstantinos Derpanis (Ryerson University), Davide Scaramuzza (University of Zurich), Philippos Mordohai (Stevens Inst. of Technology), Jean-Philippe Tardif (CMU/NREC), Irene Cheng (U. of Alberta), Yanis Pavlidis Rodrigo Carceroni(Google Labs), Rahul Swaminathan (Deutsche Telekom Labs), Xenophon Zampoulis (FORTH/CSI), Joao Barreto (University of Coimbra), Nikhil Kelshikar (CISCO), Thomas Buelow (Philips Research), Jane Mulligan (University of Colorado at Boulder).

Alumni MSE Students: Thomas Koletschka (Berkshire Robotics), Jonas Cleveland (COSY Robotics), Samarth Brahmbahtt (Georgia Tech), Barath Sanjaran (USC), Jason Liu (UCLA), Allison Mathis (ARL), Daniel Rudoy (2002, Harvard PhD), Andrew Trister (2002, MD-PhD Penn).

Teaching: Spring 2014, 2015, 2016, 2017, 2018 MEAM 620 with Vijay Kumar,

Spring 2007, 2008, Fall 2008, 2009, 2010,2011,2012,2014: CIS121 Data Structures
Fall 2006, 2007, Spring 2009, 2010, 2011,2013, Spring 2018, 2019: CIS580 Machine Perception
Fall 2016, 2015, 2004, Fall 2003, Spring 2002, Fall 2002,: CSE390 Robotics.
Fall 2000, 1999, 1998: CSE240 Introduction to Computer Architecture.
Spring 2004, 2001: CIS 700 Special Topics in Machine Perception
Spring 2003, 2000, 1999: CIS 680 Advanced Topics in Machine Perception

Education: PhD, 1992, University of Karlsruhe with Hans-Hellmut Nagel. My advisor's advisor was the Wolfgang Paul Nobel Laureate 1989 (1913-1993). Wolfgang Paul's advisor was Hans Kopfermann (1895-1963). Kopfermann's advisor was James Franck (1882-1964) Nobel Laureate 1925, Franck's advisor was Emil Warburg (1846-1931). Emil Warburg's advisor was Heinrich Gustav Magnus (1802-1870).
Diploma (Master'ss equivalent) in EE, 1986, National Technical University of Athens
Address: Department of Computer and Information Science, University of Pennsylvania, 3330 Walnut Street, Levine Hall 472, Philadelphia, PA 19104. How to reach GRASP
Acknowledgments: Grateful for support through the following grants: NSF-IIP-1439681 (I/UCRC), NSF-IIS-1703319, NSF MRI 1626008, ARL RCTA W911NF-10-2-0016, ONR N00014-17-1-2093, ARL DCIST CRA W911NF-17-2-0181, the DARPA-SRC C-BRIC, and by Honda Research Institute.

@