Scenenet rgb-d: Can 5m synthetic images beat generic imagenet pre-training on indoor segmentation? (bibtex)

by J McCormac, A Handa, S Leutenegger and AJ Davison

Reference:

Scenenet rgb-d: Can 5m synthetic images beat generic imagenet pre-training on indoor segmentation? (J McCormac, A Handa, S Leutenegger and AJ Davison), In Proceedings of the IEEE International Conference on Computer Vision, 2017.

Bibtex Entry:

@inproceedings{mccormac2017scenenet,
 title = {Scenenet rgb-d: Can 5m synthetic images beat generic imagenet pre-training on indoor segmentation?},
 author = {J McCormac and A Handa and S Leutenegger and AJ Davison},
 booktitle = {Proceedings of the IEEE International Conference on Computer Vision},
 pages = {2678--2687},
 year = {2017},
}

by J McCormac, A Handa, S Leutenegger and AJ Davison

Reference:

Bibtex Entry:

@inproceedings{mccormac2017scenenet,
 title = {Scenenet rgb-d: Can 5m synthetic images beat generic imagenet pre-training on indoor segmentation?},
 author = {J McCormac and A Handa and S Leutenegger and AJ Davison},
 booktitle = {Proceedings of the IEEE International Conference on Computer Vision},
 pages = {2678--2687},
 year = {2017},
}

Hanzhi Chen

PhD StudentTechnical University of Munich

School of Computation, Information and Technology
Informatics 9
Boltzmannstrasse 3
85748 Garching
Germany

Office: 03.09.041
Mail: Hanzhi.Chen@tum.de

Personal Website | Google Scholar | LinkedIn | GitHub

😎 Brief Bio

I am a PhD student in the Smart Robotics Lab of Technical University of Munich with Prof. Stefan Leutenegger. Previously, I received my M.Sc. degree in Robotics, Cognition, Intelligence with high distinction from Technical University of Munich.

🤖 Research Interest

Object-Centric Perception (to understand objects' geometry, concepts, affordance, and more)
Neural Scene Representations (to facilitate object-centric perception)
Few-Shot Imitation Learning (to connect embodiments' learning through object-centric representations)

🤓 Student Projects

I am always happy to work with cool folks with passion and talents. You can check my previous research works to see if there is a match between us. If you want to work with me, shoot me an email with your up-to-date transcript, résumé, and a brief comment about what research topic really interests you! This paper collection about neural fields for robotics might be helpful for you as a starting point to get inspired :)

Please refrain from inquiring me about supervision for external thesis by non-academic institutions or bachelor thesis, thank you!