WIRE: Wavelet Implicit Neural Representations

By Vishwanath Saragadam, Daniel LeJeune, Jasper Tan, Guha Balakrishnan, Ashok Narayanan Veeraraghavan, Richard Baraniuk. Computer Vision and Pattern Recognition, 2023

305 citations recorded by the source corpus.

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. A wide range of nonlinearities have been explored, but, unfortunately, current INRs designed to have high accuracy also suffer from poor robustness (to signal noise, parameter variation, etc.). Inspired by harmonic analysis, we develop a new, highly accurate and robust INR that does not exhibit this trade off. Our 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 (image denoising, image inpainting, super-resolution, computed tomography reconstruction, image over fitting, and novel view synthesis with neural radiance fields) demonstrate that WIRE defines the new state of the art in INR accuracy, training time, and robustness.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/8e7c8b3dad95122a1de1855d1482e7af25523e61

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Shahaf E. Finder
2. Roy Amoyal
3. Oren Freifeld
4. Eran Treister

In Media Technology

1. Shahaf E. Finder
2. Roy Amoyal
3. Oren Freifeld
4. Eran Treister

Citations in the corpus

• Wavelet Convolutions for Large Receptive Fields (2024, methodology): “[49] use wavelets as activation functions for implicit neural representations.”