Florian Kluger

[Florian Kluger @florian_kluger]

@sophiazhang1818 @eric_brachmann Hi Sophia, there is no longer video/presentation, but you can find the poster here: https://t.co/d9scBYfCzT
Also feel free to reach out to me if you have further questions!

[Eric Brachmann @eric_brachmann]

RGB image in, set of 3D primitives out. A #CVPR2021 paper with @florian_kluger, H. Ackermann, M. Yang and B. Rosenhahn! #ComputerVision

abs: https://t.co/mVoz8VGtc4
code: https://t.co/Vhi7PixIbm

We take RANSAC out of its comfort zone into scene understanding territory. 👇

[François Chollet @fchollet]

The only thing worse than authorities using facial recognition incompetently is authorities using facial recognition competently

[Eric Brachmann @eric_brachmann]

CONSAC (Conditional Sample Consensus). Yes, we absolutely needed another RANSAC variant. Read the paper to learn why. Presented by @florian_kluger on Tuesday 1600–1800 and 0400–0600 PST.

Video: https://t.co/hQZRayo8nW
Paper: https://t.co/L3lGDmAvP0
Code: https://t.co/bccVpf4co6

[Eric Brachmann @eric_brachmann]

2 works at #CVPR2020. I cannot attend myself (I only do conferences for the culinary surprises and comfort of the economy class). The first authors anyway do a better job at explaining our work.

Meet @AritraBhowmik6 for Reinforced Feature Points
and @florian_kluger for CONSAC!

[Eric Brachmann @eric_brachmann]

Learn how we taught #NeuralNetworks to find multiple instances of a parametric model in your outlier-infested data, eg multiple homographies in image correspondences or multiple vanishing points in a soup of line segments. #CVPR2020

If you liked NG-RANSAC, you will <3 CONSAC.

[Florian Kluger @florian_kluger]

If you are at #CVPR2020 this week, feel free to say hi during our CONSAC Q&A sessions! Tuesday, June 16, 16:00-18:00 and 04:00-06:00 PDT. @eric_brachmann @Carsten_Rother #DeepLearning #ComputerVision #MachineLearning #AI https://t.co/BjpBNHyu23