Convolution kernel adaptation to calibrated fisheye

Bruno Berenguel-Baeta (Universidad de Zaragoza),* Maria Santos-Villafranca (Universidad de Zaragoza), Jesus Bermudez-Cameo (Universidad de Zaragoza), Alejandro Perez Yus (Universidad de Zaragoza), Josechu Guerrero (Universidad de Zaragoza)
The 34th British Machine Vision Conference


Convolution kernels are the basic structural component of convolutional neural networks (CNNs). In the last years there has been a growing interest in fisheye cameras for many applications. However, the radially symmetric projection model of these cameras produces high distortions that affect the performance of CNNs, especially when the field of view is very large. In this work, we tackle this problem by proposing a method that leverages the calibration of cameras to deform the convolution kernel accordingly and adapt to the distortion. That way, the receptive field of the convolution is similar to standard convolutions in perspective images, allowing us to take advantage of pre-trained networks in large perspective datasets. We show how, with just a brief fine-tuning stage in a small dataset, we improve the performance of the network for the calibrated fisheye with respect to standard convolutions in depth estimation and semantic segmentation. The code of the calibrated deformable kernels is publicly available at



author    = {Bruno Berenguel-Baeta and Maria Santos-Villafranca and Jesus Bermudez-Cameo and Alejandro Perez Yus and Josechu Guerrero},
title     = {Convolution kernel adaptation to calibrated fisheye},
booktitle = {34th British Machine Vision Conference 2023, {BMVC} 2023, Aberdeen, UK, November 20-24, 2023},
publisher = {BMVA},
year      = {2023},
url       = {}

Copyright © 2023 The British Machine Vision Association and Society for Pattern Recognition
The British Machine Vision Conference is organised by The British Machine Vision Association and Society for Pattern Recognition. The Association is a Company limited by guarantee, No.2543446, and a non-profit-making body, registered in England and Wales as Charity No.1002307 (Registered Office: Dept. of Computer Science, Durham University, South Road, Durham, DH1 3LE, UK).

Imprint | Data Protection