[CVPR 2023] WIRE: Wavelet Implicit Neural Representations скачать в хорошем качестве

[CVPR 2023] WIRE: Wavelet Implicit Neural Representations

Implicit neural representations (INRs) have recently advanced numerous vision-related areas. INR performance depends strongly on the choice of activation function employed in its MLP network. Inspired by harmonic analysis, we develop a new, highly accurate, and robust INR that does not exhibit this tradeoff. Wavelet Implicit neural REpresentation (WIRE) uses as its activation function the complex Gabor wavelet that is well-known to be optimally concentrated in space-frequency and to have excellent biases for representing images. A wide range of experiments demonstrates that WIRE defines the new state of the art in INR accuracy, training time, and robustness. Project website: https://vishwa91.github.io/wire