Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains

NeurIPS 2020 Spotlight. This is the 3 minute talk video accompanying the paper at the virtual Neurips conference.
Project Page: bmild.github.io/fourfeat
Paper: arxiv.org/abs/2006.10739
Code: github.com/tancik/fourier-fea...
Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
Matthew Tancik*, Pratul P. Srinivasan*, Ben Mildenhall*, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan T. Barron, Ren Ng
*denotes equal contribution

[@JihyeSofiaSeoDr]

Thanks a lot! I needed to learn this for a job interview ❤

[@TheMazyProduction]

This is extremely impressive

[@xiaoyanqian6898]

Hi, thank you for the great work. I just wonder what software you used to make this video that could vividly show the iterations, the Fourier features and its Std, frequencies, and reconstruction.

[@daddu1989l]

Great work. Could you please share and teach how you created such a nice presentation?

[@erknee6071]

I find a new idea based on this paper for anomaly detection.

[@huytruonguic]

why would the datapoints you consider anomaly actually anomalies? what if the trained network happens to not be good enough to discover a subspace that makes those datapoints normal?

[@erknee6071]

@@huytruonguic You can try to design a conditional signal into the mlp, maybe regularize it with variational or sparse coding manner. You'll see something amazing is about to happen. I build this idea on medical anomaly detection and it works well. There are many properties of Fourier features not discovered in this paper.

[@davidmarquez1915]

Pluggin for SketchUp?

[@Metalwrath2]

This looks amazing, why is it not being used in GANs?

[@arminh7946]

could you explain the reason if you have gained insights by any chance?