University of Tübingen, December 2019 (phdthesis)
The motion of the world is inherently dependent on the spatial structure of the world and its geometry. Therefore, classical optical flow methods try to model this geometry to solve for the motion. However, recent deep learning methods take a completely different approach. They try to predict optical flow by learning from labelled data. Although deep networks have shown state-of-the-art performance on classification problems in computer vision, they have not been as effective in solving optical flow. The key reason is that deep learning methods do not explicitly model the structure of the world in a neural network, and instead expect the network to learn about the structure from data. We hypothesize that it is difficult for a network to learn about motion without any constraint on the structure of the world. Therefore, we explore several approaches to explicitly model the geometry of the world and its spatial structure in deep neural networks.
The spatial structure in images can be captured by representing it at multiple scales. To represent multiple scales of images in deep neural nets, we introduce a Spatial Pyramid Network (SpyNet). Such a network can leverage global information for estimating large motions and local information for estimating small motions. We show that SpyNet significantly improves over previous optical flow networks while also being the smallest and fastest neural network for motion estimation. SPyNet achieves a 97% reduction in model parameters over previous methods and is more accurate.
The spatial structure of the world extends to people and their motion. Humans have a very well-defined structure, and this information is useful in estimating optical flow for humans. To leverage this information, we create a synthetic dataset for human optical flow using a statistical human body model and motion capture sequences. We use this dataset to train deep networks and see significant improvement in the ability of the networks to estimate human optical flow.
The structure and geometry of the world affects the motion. Therefore, learning about the structure of the scene together with the motion can benefit both problems. To facilitate this, we introduce Competitive Collaboration, where several neural networks are constrained by geometry and can jointly learn about structure and motion in the scene without any labels. To this end, we show that jointly learning single view depth prediction, camera motion, optical flow and motion segmentation using Competitive Collaboration achieves state-of-the-art results among unsupervised approaches.
Our findings provide support for our hypothesis that explicit constraints on structure and geometry of the world lead to better methods for motion estimation.
NeuroImage, 202(15):116085, November 2019 (article) , Zhao, M., , , Mohler, B. J., Bartels, A., Bülthoff, I.
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019), Workshop on Aerial Swarms, November 2019 (misc) , , , , Lawless, G., , , Bülthoff, H. H.,
IEEE Robotics and Automation Letters, Robotics and Automation Letters, 4(4):4491-4498, IEEE, October 2019 (article) , , , Karlapalem, K., Bülthoff, H. H., ,
September 2019, U.S.~Patent 10,417,818 (misc) , ,
Egger, B., Smith, W. A. P., Tewari, A., Wuhrer, S., Zollhoefer, M., Beeler, T., Bernard, F.,arxiv preprint arXiv:1909.01815, September 2019 (article) , Kortylewski, A., Romdhani, S., Theobalt, C., Blanz, V., Vetter, T.
Hesse, N.,Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2019 (article) , , Arens, M., Hofmann, U., Schroeder, S.
Kenny, S.,ACM Trans. Appl. Percept., 16(1):2:1-2:18, Febuary 2019 (article) , Honda, C., ,
IEEE Transactions on Visualization and Computer Graphics, 25, pages: 1887,1897, IEEE, 2019 (article) , , , , , Hesse, N., Bülthoff, H. H.,
Black, M.J., Loper, M., Mahmood, N., Pons-Moll, G., Romero, J.December 2016, Application PCT/EP2016/064610 (misc)
Psychological Science, 27(11):1486-1497, November 2016, (article) , , Hahn, C. A., , O’Toole, A. J.
ETH Zurich, July 2016 (phdthesis)
ACM Trans. Graph. (Proc. SIGGRAPH), 35(4):54:1-54:14, July 2016 (article) , , Hill, M. Q., Hahn, C. A., , O’Toole, A.,
International Journal of Computer Vision (IJCV), 118(2):172-193, June 2016 (article) , Ballan, L., , Aponte, P., Pollefeys, M.,
Marcard, T. V.,Transactions on Pattern Analysis and Machine Intelligence PAMI, 38(8):1533-1547, January 2016 (article) , Rosenhahn, B.
Robotics and Autonomous Systems, 83, pages: 275-286, 2016 (article) , Bülthoff, H.
Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, 0(0):1-8, 2016 (article) , , , Machann, J.,
Feix, T.,Human-Machine Systems, IEEE Transactions on, 46(1):66-77, 2016 (article) , Schmiedmayer, H., Dollar, A., Kragic, D.
Brubaker, M. A.,IEEE Trans. on Pattern Analysis and Machine Intelligence (PAMI), 2016 (article) , Urtasun, R.
IEEE Transactions on Image Processing, 20(12):3393-3405, IEEE Signal Processing Society, December 2011 (article) , Tai, Y., Shin, S. Y.
Journal of Vision, 11(11):507-507, ARVO, September 2011 (article) , Sinha, P.
Dhandhania, K.,Journal of Vision, 11(11):800-800, ARVO, September 2011 (article) , Sinha, P.
Messias, J.,15th Annual RoboCup International Symposium 2011, July 2011 (techreport) , Reis, J., Sousa, J., Lima, P.
Pattern Analysis and Machine Intelligence, IEEE Transactions on, 33(7):1442-1456, IEEE, July 2011 (article) , Sheikh, Y., Khan, S., Kanade, T.
Sigal, L., Isard, M., Haussecker, H.,International Journal of Computer Vision, 98(1):15-48, Springer Netherlands, May 2011 (article)
Kim, S., Simeral, J. D., Hochberg, L. R., Donoghue, J. P., Friehs, G. M.,IEEE Transactions on Neural Systems and Rehabilitation Engineering, 19(2):193-203, April 2011 (article)
Baker, S., Scharstein, D., Lewis, J. P., Roth, S.,International Journal of Computer Vision, 92(1):1-31, March 2011 (article) , Szeliski, R.
(J. Neural Engineering Highlights of 2011 Collection. JNE top 10 cited papers of 2010-2011.)
Simeral, J. D., Kim, S.,J. of Neural Engineering, 8(2):025027, 2011 (article) , Donoghue, J. P., Hochberg, L. R.
PhD Thesis, MIT, 2011 (techreport)
Igor Sazonov, Si Yong Yeo, Rhodri Bevan, Xianghua Xie, Raoul van Loon, Perumal NithiarasuInternational Journal for Numerical Methods in Biomedical Engineering, 27(12):1868–1910, 2011 (article)
Si Yong Yeo, Xianghua Xie, Igor Sazonov, Perumal NithiarasuIEEE Transactions on Image Processing, 20(5):1373 - 1387, 2011 (article)
Soren HaubergUniversity of Copenhagen, 2011 (phdthesis)
Prihambodo Saksono, Perumal Nithiarasu, Igor Sazonov, Si Yong YeoInternational Journal for Numerical Methods in Biomedical Engineering, 87(1-5):96–114, 2011 (article)
Soren Hauberg, Kim S. PedersenInternational Journal of Computer Vision, 94, pages: 317-334, Springer Netherlands, 2011 (article)
(148), Max Planck Institute, 2006 (techreport) ,
Sigal, L.,(CS-06-08), Brown University, Department of Computer Science, 2006 (techreport)
Wu, W., Gao, Y., Bienenstock, E., Donoghue, J. P.,Neural Computation, 18(1):80-118, 2006 (article)
Wood, F.,IEEE Trans. Biomedical Engineering, 51(6):912-918, June 2004 (article) , Vargas-Irwin, C., Fellows, M., Donoghue, J. P.
Wu, W.,IEEE Trans. Biomedical Engineering, 51(6):933-942, June 2004 (article) , Mumford, D., Gao, Y., Bienenstock, E., Donoghue, J. P.
Sidenbladh, H.,International Journal of Computer Vision, 54(1-3):183-209, August 2003 (article)
De la Torre, F.,International Journal of Computer Vision, 54(1-3):117-142, August 2003 (article)
International Journal of Computer Vision, 54(1-3):5-11, August 2003 (article) , Kimia, B.
De la Torre, F.,Computer Vision and Image Understanding, 91(1-2):53-71, July 2003 (article)
IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(10):972-986, October 1996 (article) , Jepson, A.
International Journal of Computer Vision , 19(1):57-92, July 1996 (article) , Rangarajan, A.
Jepson, A.,PRECARN ARK Project Technical Report ARK96-PUB-54, March 1996 (techreport)
Computer Vision and Image Understanding, 63(1):75-104, January 1996 (article) , Anandan, P.
Yale University, Department of Computer Science, New Haven, CT, 1992, Research Report YALEU-DCS-RR-923 (phdthesis)