Learning Local Implicit Fourier Representation for Image Warping

07/05/2022
by   Jaewon Lee, et al.
0

Image warping aims to reshape images defined on rectangular grids into arbitrary shapes. Recently, implicit neural functions have shown remarkable performances in representing images in a continuous manner. However, a standalone multi-layer perceptron suffers from learning high-frequency Fourier coefficients. In this paper, we propose a local texture estimator for image warping (LTEW) followed by an implicit neural representation to deform images into continuous shapes. Local textures estimated from a deep super-resolution (SR) backbone are multiplied by locally-varying Jacobian matrices of a coordinate transformation to predict Fourier responses of a warped image. Our LTEW-based neural function outperforms existing warping methods for asymmetric-scale SR and homography transform. Furthermore, our algorithm well generalizes arbitrary coordinate transformations, such as homography transform with a large magnification factor and equirectangular projection (ERP) perspective transform, which are not provided in training.

READ FULL TEXT

page 10

page 11

page 12

research
11/17/2021

Local Texture Estimator for Implicit Representation Function

Recent works with an implicit neural function shed light on representing...
research
06/21/2023

Dynamic Implicit Image Function for Efficient Arbitrary-Scale Image Representation

Recent years have witnessed the remarkable success of implicit neural re...
research
08/07/2022

Adaptive Local Implicit Image Function for Arbitrary-scale Super-resolution

Image representation is critical for many visual tasks. Instead of repre...
research
08/26/2023

Neural Implicit Morphing of Face Images

Face morphing is one of the seminal problems in computer graphics, with ...
research
03/05/2023

Super-Resolution Neural Operator

We propose Super-resolution Neural Operator (SRNO), a deep operator lear...
research
02/01/2022

On Regularizing Coordinate-MLPs

We show that typical implicit regularization assumptions for deep neural...
research
09/01/2021

Seeing Implicit Neural Representations as Fourier Series

Implicit Neural Representations (INR) use multilayer perceptrons to repr...

Please sign up or login with your details

Forgot password? Click here to reset