About Us


George Toderici


George Toderici received his Ph.D. in Computer Science from the University of Houston in 2007 where his research focused on 2D-to-3D face recognition, and joined Google in 2008. His current work at Google Research is focused on lossy multimedia compression using neural networks. His past projects at Google include the design of neural-network architectures and classical approaches for video classification, action recognition, YouTube channel recommendations, and video enhancement. He has helped organize the THUMOS-2014 and YouTube-8M (CVPR 2017, ECCV 2018) video classification challenges, and contributed to the design of the Sports-1M dataset. He has also served as Area Chair for the ACM Multimedia Conference in 2014, and is a regular reviewer for CVPR, ICCV, and NIPS.Read More

Wenzhe Shi


Wenzhe Shi works at Magic Pony of Twitter as a computer vision research lead. He received his Ph.D. training under Prof. Daniel Rueckert in the Biomedical Image Analysis group within Imperial College London from 2009 to 2012 where he stayed as a research associate from 2012 to 2014. He joined Magic Pony 2015 as on e of the first employees. The company was acquired by Twitter for 150M in 2016. He has published over 100 scientific papers in top-tier academic journals and conferences, and is inventor of more than 20 patents. His projects at Twitter includes super-resolution, compression, frame interpolation, image/video classification and recommendation. Wenzhe has also served as a regular reviewer for some of the top computer vision and medical image analysis journals and conferences (CVPR, ICCV, MICCAI, IEEE-TMI, IEEE-MEDIA, etc).Read More

Radu Timofte

ETH Zurich

Radu Timofte is research group leader in the Computer Vision Laboratory, at ETH Zurich, Switzerland. He obtained a PhD degree in Electrical Engineering at the KU Leuven, Belgium in 2013, the MSc at the Univ. of Eastern Finland in 2007, and the Dipl. Eng. at the Technical Univ. of Iasi, Romania in 2006. He serves a s a reviewer for top journals (such as TPAMI, TIP, IJCV, TNNLS, TCSVT, CVIU, PR) and conferences (ICCV, CVPR, ECCV, NIPS), as area chair for ACCV 2018 and as area editor for Elsevier’s CVIU journal. His work received a best scientific paper award at ICPR 2012, the best paper award at CVVT workshop (ECCV 2012), the best paper award at ChaLearn LAP workshop (ICCV 2015), the best scientific poster award at EOS 2017, the honorable mention award at FG 2017, and his team won a number of challenges including traffic sign detection (IJCNN 2013) and apparent age estimation (ICCV 2015). He is co-founder of Merantix and organizer of NTIRE ‘16, ’17 and ’18 events. His current research interests include sparse and collaborative representations, deep learning, optical flow, compression, image restoration and enhancement.Read More

Lucas Theis


Lucas Theis is a machine learning researcher at Twitter. He studied Cognitive Science in Osnabrück before starting a PhD at the Max Planck Research School in Tübingen, Germany, in 2009. Here, he worked on generative modeling of natural images with Matthias Bethge, in particular using deep learning. After finishing his PhD, he started to work on image compression and super-resolution for Magic Pony Technologies in London – a startup which got acquired by Twitter in 2016. Other work includes papers on variational inference, saliency prediction, and computational neuroscience. Lucas has served as a reviewer for some of the top machine learning journals and conferences (JMLR, CVPR, ICML, NIPS, ICLR).Read More

Johannes Ballé


Johannes Ballé received his PhD in Electrical Engineering from RWTH Aachen University in 2013. He then worked at New York University's Center for Neural Science as a postdoc until early 2017, when he joined Google in Mountain View. His work revolves around classical topics of signal processing; image and video com pression; representation of images using generative and probabilistic models; and models of visual perception of texture, as well as images in general. He has served as a reviewer of numerous publications in the fields of image compression and signal processing (e.g., IEEE Transactions on Image Processing, Picture Coding Symposium).Read More

Eirikur Agustsson

Google / ETH Zurich

Eirikur Agustsson will soon defend his PhD thesis at the Computer Vision Lab of ETH Zurich and has recently joined Google as a Research Scientist within the Machine Intelligence group. He has mainly worked on image and network compression using neural networks, almost lossless analog compression, image-super-resol ution and generative adversarial networks. He has reviewed for many of the top computer vision and machine learning conferences and journals (such as NIPS, CVPR and IEEE Transactions on Pattern Analysis and Machine Intelligence) and co-organized numerous workshops (the WebVision challenge & workshop at CVPR '17 and '18, the NTIRE challenge & workshop at CVPR '17 and CLIC at CVPR '18).Read More

Nick Johnston


Nick Johnston works as a Software Engineer within the Machine Intelligence group at Google. He has previously published image compression work at CVPR. His research interests are in leveraging the power of deep learning and computer vision for improved rate-distortion performance in image compression. Additionally , he is interested in neural network optimization for mobile devices and embedded systems. Nick received his BSc in Computer Engineering from Iowa State University.Read More

Fabian Mentzer

ETH Zurich

Fabian Mentzer studied Information Technology and Electrical Engineering at ETH Zurich, with a focus on information and communication theory. He is now a second year PhD candidate at the Computer Vision Lab of ETH Zurich, under the supervision of Prof. Luc Van Gool. His focus is on improving learned image compress ion using deep neural networks and investigating the feature representations learned by such networks, with works published at NIPS, ICLR and CVPR so far.Read More