CoordGate: efficiently computing spatially-varying convolutions in convolutional neural networks
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....
Main Authors: | Howard, S, Norreys, P, Döpp, A |
---|---|
Format: | Conference item |
Language: | English |
Published: |
British Machine Vision Association
2023
|
Similar Items
-
Convolutional Neural Network with Spatial-Variant Convolution Kernel
by: Yongpeng Dai, et al.
Published: (2020-08-01) -
Efficient Gated Convolutional Recurrent Neural Networks for Real-Time Speech Enhancement
by: Fazal-E -Wahab, et al.
Published: (2025-01-01) -
Process tomography of structured optical gates with convolutional neural networks
by: Tareq Jaouni, et al.
Published: (2024-01-01) -
An energy-efficient convolution unit for depthwise separable convolutional neural networks
by: Chong, Yi Sheng, et al.
Published: (2021) -
Efficient field‐programmable gate array‐based reconfigurable accelerator for deep convolution neural network
by: Xianghong Hu, et al.
Published: (2021-03-01)