CoordGate: efficiently computing spatially-varying convolutions in convolutional neural networks

Conference item

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 existing approaches, offering a more robust and spatially aware solution for CNNs in various computer vision applications.

Authors: Howard, S; Norreys, P; Döpp, A

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: British Machine Vision Association
• Article number: 0744
• Publication date: 2023-11-24
• Acceptance date: 2023-08-25
• Event title: 34th British Machine Vision Conference (BMVC 2023)
• Event location: Aberdeen, Scotland
• Event website: https://www.bmva.org/bmvc
• Event start date: 2023-11-20
• Event end date: 2023-11-24
• Language: English