University of Cambridge > > CUED Computer Vision Research Seminars > Machine Learning Techniques for 3D Registration with Images

Machine Learning Techniques for 3D Registration with Images

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Geraldine Duggan.

Professor Lepetit will present 3 recent works that rely on statistical learning, and mostly deep learning, for 3D registration. The first work introduces a novel representation of 3D parts that is well adapted to the 3D registration of textureless, possible occluded objects. The second part will present a method that learns how to detect feature points stable to drastic light changes. The third one shows how to train a feedback loop end-to-end to register the 3D pose of a hand using depth maps. This last method is currently the best performing one on hand pose benchmarks.

This talk is part of the CUED Computer Vision Research Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2023, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity