Shared-kernel Wavelet Neural Networks for Poisson Image Reconstruction

TL;DR

This paper introduces a compact, real-time neural network method that reconstructs images from their sparse Laplacian fields by solving Poisson equations, outperforming previous techniques in accuracy and efficiency.

Contribution

The paper proposes a shared-kernel wavelet neural network for Poisson image reconstruction, featuring fewer parameters, linear complexity, and higher accuracy than existing methods.

Findings

The Laplacian field of images is sparse and follows a stable distribution.

The proposed neural network achieves real-time reconstruction with high accuracy.

The method is effective for various applications like image compression and low light enhancement.

Abstract

The Laplacian operator transforms the image into its Laplacian field, which usually is sparse and satisfies a stable distribution. On the other hand, an image can be uniquely reconstructed from its Laplacian field via solving a Poisson equation with a proper boundary condition. Such uniqueness is mathematically guaranteed. Thanks to these properties, we propose to use the sparse Laplacian field to present the image. We first show that the Laplacian field is sparse and satisfies a stable distribution on hundreds images. Then, we show that the image can be accurately reconstruct from its Laplacian field. For the reconstruction task, we propose a shared-kernel wavelet neural network, which solves the Poisson equation and has three advantages. First, it has less than {\bf 0.0002M} parameters, which is compact enough for most of devices. Second, it has linear computation complexity, leading to a real-time reconstruction. Third, it achieves higher accuracy than previous methods. Several numerical experiments are conducted to show the effectiveness and efficiency of the sparse Laplacian field and the proposed Poisson solver. The proposed method can be applied in a large range of applications such as image compression, low light enhancement, object tracking, etc.