CoordGate: Efficiently Computing Spatially-Varying Convolutions in Convolutional Neural Networks

TL;DR

CoordGate introduces a lightweight module for CNNs that efficiently computes spatially-varying convolutions, improving image deblurring by enabling spatially adaptive filtering.

Contribution

It presents a novel CoordGate module that uses coordinate encoding and gating to efficiently handle spatially-varying convolutions in CNNs.

Findings

Outperforms conventional methods in image deblurring.

Enables spatially adaptive filtering within CNN architectures.

Demonstrates robustness across different computer vision tasks.

Abstract

Optical imaging systems are inherently limited in their resolution due to the point spread function (PSF), which applies a static, yet spatially-varying, convolution to the image. This degradation can be addressed via Convolutional Neural Networks (CNNs), particularly through deblurring techniques. However, current solutions face certain limitations in efficiently computing spatially-varying convolutions. In this paper we propose CoordGate, a novel lightweight module that uses a multiplicative gate and a coordinate encoding network to enable efficient computation of spatially-varying convolutions in CNNs. CoordGate allows for selective amplification or attenuation of filters based on their spatial position, effectively acting like a locally connected neural network. The effectiveness of the CoordGate solution is demonstrated within the context of U-Nets and applied to the challenging problem of image deblurring. The experimental results show that CoordGate outperforms conventional approaches, offering a more robust and spatially aware solution for CNNs in various computer vision applications.