Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenes

How can we create large training sets for deep neural networks while avoiding labor intensive annotation of real images or expensive creation of synthetic content? We suggest near photo-realistic augmentation of real images with synthetic objects to combine the best of both worlds. The extended version of our BMVC’17 paper investigates which aspects matter most […]

More Info

Oliver Groth wins Carl Zeiss Diplompreis

Oliver Groth has won the Carl Zeiss Diplompreis for his Diplom thesis on the topic “Visual Phrase Grounding with Variable Supervision in an EM-RNN Framework”, written at CVLD and Stanford Vision Lab. Abstract The localization of natural language phrases in images (also know as grounding) is an emerging task in Computer Vision having important applications […]

More Info

6D Object Pose Workshop and SIXD Challenge at ICCV2017

We are co-organizing the 3rd International Workshop on Recovering 6D Object Pose in conjuction with ICCV 2017, Venice. Part of the workshop is a challenge on the task of 6D localization of a single instance of a single object. The invited speakers are: Stefan Hinterstoisser​, Google X Michael Bronstein, USI Lugano, Intel Guru Krishnan, Amazon Abhinav […]

More Info

7 papers at CVPR 17; 2 papers at ICRA 2017 and 1 paper at ISBI 2017

Seven papers accepted to CVPR 17. One paper accepted to ISBI 2017: Using noisy crowd sourcing data to segment the microscopic image of a flywing Two papers accepted to ICRA 2017: Joint work with Phil Torr’s team (Daniela Massiceti) in Oxford on mapping Regression Trees on CNNs A new state-of-the-art for semantic segmentation and depth […]

More Info

Jakob Kruse wins Carl Zeiss Diplompreis

Jakob Kruse has won the Carl Zeiss Diplompreis for his Master’s thesis on the topic “Comparison of Learned Inference Approaches for Image Restoration”, written at CVLD.

More Info