Radu Timofte
【Bio】Researcher, Leader of a group
【Focus on】Multi-Class Multi-View Object Detection, Recognition, Segmentation, Tracking, Sparse and Collaborative Representations

  • 2017 Arxiv WESPE: Weakly Supervised Photo Enhancer for Digital Cameras
  • 2017 ICCV In Defense of Shallow Learned Spectral Reconstruction from RGB Images
  • 2017 ABC-GAN: Adaptive Blur and Control for improved training stability of Generative Adversarial Networks
  • 2017 Arxiv Soft-to-Hard Vector Quantization for End-to-End Learned Compression of Images and Neural Networks
  • 2017 Arxiv Single Image Super Resolution-When Model Adaptation Matters
  • 2017 Arxiv On the Relation between Color Image Denoising and Classification
  • 2017 ICCV DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks
  • 2016 ICPR Anchored Fusion for Image Restoration
  • 2016 ARXIV k2-means for fast and accurate large scale clustering
  • 2016 TIP Demosaicing based on Directional Difference Regression and Efficient Regression Priors
  • 2016 CVPR Deep Features or Not: Temperature and Time Prediction in Outdoor Scenes
  • 2016 CVPR Structured Output SVM Prediction of Apparent Age, Gender and Smile From Deep Features
  • 2016 CVIU PICASO: PIxel Correspondences And SOft Match Selection for Real-time Tracking
  • 2015 ICIP Efficient Regression Priors for Post-processing Demosaiced Images
  • 2015 JCG  Jointly Optimized Regressors for Image Super-resolution
  • 2015 EG Jointly Optimized Regressors for Image Super-resolution
  • 2015 WACV SparseFlow: Sparse Matching for Small to Large Displacement Optical Flow
  • 2014 ACCV A+: Adjusted Anchored Neighborhood Regression for Fast Super-Resolution
  • 2014 PR Iterative Nearest Neighbors
  • 2014 WACV Scale-Invariant Line Descriptors for Wide Baseline Matching
  • 2013 ICCV Anchored Neighborhood Regression for Fast Example-Based Super-Resolution
  • 2014 PRL Adaptive and Weighted Collaborative Representations for Image Classification

Davide Scaramuzza
【Bio】Professor, leader of a group
【Focus on】Medical Image Analysis and Visualization, Object Recognition, Gesture Analysis, Tracking, and Scene Understanding and Modeling

  • 2018 RAL On the Comparison of Gauge Freedom Handling in Optimization-based Visual-Inertial State Estimation
  • 2018 IROS PAMPC: Perception-Aware Model Predictive Control for Quadrotors
  • 2018 ICRA Data-Efficient Decentralized Visual SLAM
  • 2018 RAL Differential Flatness of Quadrotor Dynamics Subject to Rotor Drag for Accurate Tracking of High-Speed Trajectories
  • 2017 BMVC Fast Event-based Corner Detection
  • 2017 RAL Thrust Mixing, Saturation, and Body-Rate Control for Accurate Aggressive Quadrotor Flight
  • 2016 ICRA An Information Gain Formulation for Active Volumetric 3D Reconstruction
  • 2014 ICRA REMODE: Probabilistic, Monocular Dense Reconstruction in Real Time
  • 2014 ICRA SVO: Fast Semi-Direct Monocular Visual Odometry
  • 2014 ICRA A Monocular Pose Estimation System based on Infrared LEDs
  • 2014 IROS Event-based, 6-DOF Pose Tracking for High-Speed Maneuvers
  • 2014 ICRA Micro Air Vehicle Localization and Position Tracking from Textured 3D Cadastral Models
  • 2011 CVPR A Novel Parameterization of the Perspective-Three-Point Problem for a Direct Computation of Absolute Camera Position and Orientation
  • 2009 IJRA A Robust Descriptor for Tracking Vertical Lines in Omnidirectional Images and its Use in Mobile Robotics
  • 2006 IROS A Toolbox for Easily Calibrating Omnidirectional Cameras

Luc Van Gool Luc Van Gool
【Bio】Professor, leader of a group
【Focus on】Medical Image Analysis and Visualization, Object Recognition, Gesture Analysis, Tracking, and Scene Understanding and Modeling

  • SURF FeatureDetector
  • k Adjacent Segmentsdetector
  • Camera Calibrationand Hand to Eye Calibration (Hand-Eye Calibration) Toolbox
  • SEEDS: SuperpixelsExtracted via Energy-Driven Sampling
  • Randomized Prim’sfor Object Proposals


  • Food 101
  • ETHZ RueMonge 2014
  • Biwi Kinect Head Pose Database
  • BIWI 3D Audiovisual Corpus of Affective Communication – B3D(AC)^2
  • BIWI 3D Audiovisual Corpus of Affective Communication – B3D(AC)^2
  • ETHZ Shape Classes
  • ETHZ Extended Shape Classes
  • ETH Face Pose Range Image Data Set
  • “Central” Pedestrian Crossing Sequences
  • Zurich Buildings Database
  • ETHZ Personal Event Collection

Helmut Grabner Helmut Grabner
【Bio】Researcher at Logitech, Postdoc at Ethz, not updated since 2015
【Focus on】video summarization, object detection, tracking, recognition and event detection, in particular in the field of visual surveillance

  • 2014 ECCV Creating Summaries from User Videos
  • 2009 ICCV Beyond Semi-Supervised Tracking: Tracking Should Be as Simple as Detection, but not Simpler than Recognition
  • 2008 ECCV Semi-supervised On-line Boosting for Robust Tracking
  • 2006 BMVC Real-time Tracking via On-line Boosting

Stefan Roth Stefan Roth
【Bio】An insititute
【Focus on】convert image-like sensor data into models of the world

  • 2017 ICCV Semantically Informed Multiview Surface Refinement
  • 2017 CVPR SupReME: Super-Resolution for multispectral Multiresolution Estimation
  • 2015 ICCV Massively Parallel Multiview Stereopsis by Surface Normal Diffusion
  • 2015 ICCV Hyperspectral Image Super Resolution
  • 2015 IJSPRS Global Consistent Point Cloud Registration
  • 2015 IJCV Piecewise rigid scene flow
  • 2015 TGRS RQE Feature Extraction
  • 2015 ISPRS Globally Consistent Registration of Multiple Point Clouds
  • 2014 IJSPRS K-4PCS Pairwise Registration
  • 2014 CVPR Predicting Matchability
  • 2014 ECCV VocMatch: Efficient Multiview Correspondence for Structure from Motion
  • 2014 CVPR Are Cars Just 3D Boxes? – Jointly Estimating the 3D Shape of Multiple Objects
  • 2013 CVPR Explicit Occlusion Modeling for 3D Object Class Representations
  • 2012 CVPR Multi-Target Tracking
  • A GPU implementation of the popular SURF method in C++/CUDA
  • 2008 CVPR Action Snippets
  • 2007 ICCV Coupled Detection and Trajectory Estimation for Multi-Object Tracking
  • 2013 PR detection by elastic shape matching

Marc Pollefeys Marc Pollefeys
【Bio】Professor, leader of a group, previously worked at UNC
【Focus on】extract 3D shape, motion, appearance and calibration information from images