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.
Would it be feasible to somehow incorporate the fourier features in the activation functions? So that the entire model can be made high frequency sensitive instead of just the input
You can just use Discrete Cosine Transform to do it. It's much simpler. No need to use Fourier transform to make it complex. We have a paper: www.cse.scu.edu/~yliu1/papers/ISCAS2020Yifei.pdf You can write 2D-DCT into 1 dimensional representation for activation function. See our another paper: www.cse.scu.edu/~yliu1/papers/ISCAS2021YifeiPei.pdf
![[ECCV 2020] NeRF: Neural Radiance Fields (10 min talk)](/img/n.gif)
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.
Thank you so much for this wonderful video!
Great video, especially the part with the scale is well explained
You can just use Discrete Cosine Transform to do it. We have a paper: www.cse.scu.edu/~yliu1/papers/ISCAS2020Yifei.pdf
A+ in my book.
Would it be feasible to somehow incorporate the fourier features in the activation functions? So that the entire model can be made high frequency sensitive instead of just the input
You can just use Discrete Cosine Transform to do it. It's much simpler. No need to use Fourier transform to make it complex. We have a paper: www.cse.scu.edu/~yliu1/papers/ISCAS2020Yifei.pdf You can write 2D-DCT into 1 dimensional representation for activation function. See our another paper: www.cse.scu.edu/~yliu1/papers/ISCAS2021YifeiPei.pdf
However, these transforms can only work on fully-connected neural networks. It gives bad results on CNN.
😮