English

Learning Local Implicit Fourier Representation for Image Warping

Computer Vision and Pattern Recognition 2022-07-06 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2207.01831,
  title  = {Learning Local Implicit Fourier Representation for Image Warping},
  author = {Jaewon Lee and Kwang Pyo Choi and Kyong Hwan Jin},
  journal= {arXiv preprint arXiv:2207.01831},
  year   = {2022}
}

Comments

ECCV 2022 camera-ready version (https://ipl.dgist.ac.kr/LTEW.pdf)

R2 v1 2026-06-24T12:14:04.785Z