Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains (Jun 2020 ArXiV)
andrewjong opened this issue · comments
0. Article Information and Links
- Paper link: https://people.eecs.berkeley.edu/~bmild/fourfeat/
- Release date: YYYY/MM/DD
- Number of citations (as of 2020/MM/DD):
- Implementation code: https://github.com/tancik/fourier-feature-networks
- Supplemental links (e.g. results):
- Publication: Conference YYYY
1. What do the authors try to accomplish?
2. What's great compared to previous research?
3. Where are the key elements of the technology and method?
- Compare 4 types of Fourier Feature encoding
Tasks
Direct regression.
- (x, y) to (r, g, b)
4. How did you verify that it works?
5. Things to discuss? (e.g. weaknesses, potential for future work, relation to other work)
6. Are there any papers to read next?
Related concurrent work: Sinusoidal Representation Networks https://vsitzmann.github.io/siren/