Bruno Berenguel-Baeta
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Bruno Berenguel-Baeta has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Jose Jesus Guerrero
Aragón Institute for Engineering Research (I3A), University of Zaragoza, Zaragoza, Spain
5 shared publications - Jesus Bermudez-Cameo
Universidad de Zaragoza
4 shared publications Jesus Bermudez-Cameo
2 shared publicationsJose J. Guerrero
Instituto de Investigacion Ingenieria Aragon Universidad Zaragoza Zaragoza Spain
2 shared publications- Alejandro Perez-Yus
Departamento de Informatica e Ingenieria de Sistemas, Universidad de Zaragoza, Zaragoza Spain 50018
1 shared publication Jesus Bermudez‐Cameo
Instituto de Investigacion Ingenieria Aragon Universidad Zaragoza Zaragoza Spain
1 shared publication
Latest Publications
- Open Access
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 19 (1)
Panoramic Depth and Semantic Estimation With Frequency and Distortion Aware Convolutions
Omnidirectional images reveal advantages when addressing the understanding of the environment due to the 360‐degree contextual information. However, the inherent characteristics of the omnidirectional images add additional problems to obtain an accurate detection and segmentation of objects or a good depth estimation. To overcome these problems, we exploit convolutions in the frequency domain, obtaining a wider receptive field in each convolutional layer, and convolutions in the equirectangular projection, to cope with the image distortion. Both convolutions allow to leverage the whole context information from omnidirectional images. Our experiments show that our proposal has better performance on non‐gravity‐oriented panoramas than state‐of‐the‐art methods and similar performance on oriented panoramas as specific state‐of‐the‐art methods for semantic segmentation and for monocular depth estimation, outperforming the sole other method which provides both tasks.
- 1 January 2025
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 19 (1)
Open AccessPanoramic Depth and Semantic Estimation With Frequency and Distortion Aware Convolutions
Omnidirectional images reveal advantages when addressing the understanding of the environment due to the 360‐degree contextual information. However, the inherent characteristics of the omnidirectional images add additional problems to obtain an accurate detection and segmentation of objects or a good depth estimation. To overcome these problems, we exploit convolutions in the frequency domain, obtaining a wider receptive field in each convolutional layer, and convolutions in the equirectangular projection, to cope with the image distortion. Both convolutions allow to leverage the whole context information from omnidirectional images. Our experiments show that our proposal has better performance on non‐gravity‐oriented panoramas than state‐of‐the‐art methods and similar performance on oriented panoramas as specific state‐of‐the‐art methods for semantic segmentation and for monocular depth estimation, outperforming the sole other method which provides both tasks.
- Open Access
FreDSNet: Joint Monocular Depth and Semantic Segmentation with Fast Fourier Convolutions
In this work we present FreDSNet, a deep learning solution which obtains semantic 3D understanding of indoor environments from single panoramas. Omnidirectional images reveal task-specific advantages when addressing scene understanding problems due to the 360-degree contextual information about the entire environment they provide. However, the inherent characteristics of the omnidirectional images add additional problems to obtain an accurate detection and segmentation of objects or a good depth estimation. To overcome these problems, we exploit convolutions in the frequential domain obtaining a wider receptive field in each convolutional layer. These convolutions allow to leverage the whole context information from omnidirectional images. FreDSNet is the first network that jointly provides monocular depth estimation and semantic segmentation from a single panoramic image exploiting fast Fourier convolutions. Our experiments show that FreDSNet has similar performance as specific state of the art methods for semantic segmentation and depth estimation. FreDSNet code is publicly available in https://github.com/Sbrunoberenguel/FreDSNet
Open AccessFreDSNet: Joint Monocular Depth and Semantic Segmentation with Fast Fourier Convolutions
In this work we present FreDSNet, a deep learning solution which obtains semantic 3D understanding of indoor environments from single panoramas. Omnidirectional images reveal task-specific advantages when addressing scene understanding problems due to the 360-degree contextual information about the entire environment they provide. However, the inherent characteristics of the omnidirectional images add additional problems to obtain an accurate detection and segmentation of objects or a good depth estimation. To overcome these problems, we exploit convolutions in the frequential domain obtaining a wider receptive field in each convolutional layer. These convolutions allow to leverage the whole context information from omnidirectional images. FreDSNet is the first network that jointly provides monocular depth estimation and semantic segmentation from a single panoramic image exploiting fast Fourier convolutions. Our experiments show that FreDSNet has similar performance as specific state of the art methods for semantic segmentation and depth estimation. FreDSNet code is publicly available in https://github.com/Sbrunoberenguel/FreDSNet
- Open Access
Convolution kernel adaptation to calibrated fisheye
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.
Open AccessConvolution kernel adaptation to calibrated fisheye
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.
- Open Access
- 10 June 2022
- Published by Elsevier in Data in Brief
- Vol. 43, 108375
Non-central panorama indoor dataset
- 10 June 2022
- Published by Elsevier in Data in Brief
- Vol. 43, 108375
Open AccessNon-central panorama indoor dataset
- Open Access
- 26 April 2022
- Published by Elsevier in Pattern Recognition
- Vol. 129
Atlanta scaled layouts from non-central panoramas
- 26 April 2022
- Published by Elsevier in Pattern Recognition
- Vol. 129
Open AccessAtlanta scaled layouts from non-central panoramas
- Open Access
- 22 December 2020
- Published by Universidad de Zaragoza in Jornada de Jóvenes Investigadores del I3A
- Vol. 8
Omnidirectional Image Data-Set for Computer Vision Applications
In this paper we present an image data-set of different omnidirectional systems. The images include full information of colour, depth, instance segmentation and room layout. This dataset aims to help in the training and test of different neural networks and development of computer vision algorithms.
- 22 December 2020
- Published by Universidad de Zaragoza in Jornada de Jóvenes Investigadores del I3A
- Vol. 8
Open AccessOmnidirectional Image Data-Set for Computer Vision Applications
In this paper we present an image data-set of different omnidirectional systems. The images include full information of colour, depth, instance segmentation and room layout. This dataset aims to help in the training and test of different neural networks and development of computer vision algorithms.
- Open Access
OmniSCV: An Omnidirectional Synthetic Image Generator for Computer Vision
Omnidirectional and 360° images are becoming widespread in industry and in consumer society, causing omnidirectional computer vision to gain attention. Their wide field of view allows the gathering of a great amount of information about the environment from only an image. However, the distortion of these images requires the development of specific algorithms for their treatment and interpretation. Moreover, a high number of images is essential for the correct training of computer vision algorithms based on learning. In this paper, we present a tool for generating datasets of omnidirectional images with semantic and depth information. These images are synthesized from a set of captures that are acquired in a realistic virtual environment for Unreal Engine 4 through an interface plugin. We gather a variety of well-known projection models such as equirectangular and cylindrical panoramas, different fish-eye lenses, catadioptric systems, and empiric models. Furthermore, we include in our tool photorealistic non-central-projection systems as non-central panoramas and non-central catadioptric systems. As far as we know, this is the first reported tool for generating photorealistic non-central images in the literature. Moreover, since the omnidirectional images are made virtually, we provide pixel-wise information about semantics and depth as well as perfect knowledge of the calibration parameters of the cameras. This allows the creation of ground-truth information with pixel precision for training learning algorithms and testing 3D vision approaches. To validate the proposed tool, different computer vision algorithms are tested as line extractions from dioptric and catadioptric central images, 3D Layout recovery and SLAM using equirectangular panoramas, and 3D reconstruction from non-central panoramas.
Open AccessOmniSCV: An Omnidirectional Synthetic Image Generator for Computer Vision
Omnidirectional and 360° images are becoming widespread in industry and in consumer society, causing omnidirectional computer vision to gain attention. Their wide field of view allows the gathering of a great amount of information about the environment from only an image. However, the distortion of these images requires the development of specific algorithms for their treatment and interpretation. Moreover, a high number of images is essential for the correct training of computer vision algorithms based on learning. In this paper, we present a tool for generating datasets of omnidirectional images with semantic and depth information. These images are synthesized from a set of captures that are acquired in a realistic virtual environment for Unreal Engine 4 through an interface plugin. We gather a variety of well-known projection models such as equirectangular and cylindrical panoramas, different fish-eye lenses, catadioptric systems, and empiric models. Furthermore, we include in our tool photorealistic non-central-projection systems as non-central panoramas and non-central catadioptric systems. As far as we know, this is the first reported tool for generating photorealistic non-central images in the literature. Moreover, since the omnidirectional images are made virtually, we provide pixel-wise information about semantics and depth as well as perfect knowledge of the calibration parameters of the cameras. This allows the creation of ground-truth information with pixel precision for training learning algorithms and testing 3D vision approaches. To validate the proposed tool, different computer vision algorithms are tested as line extractions from dioptric and catadioptric central images, 3D Layout recovery and SLAM using equirectangular panoramas, and 3D reconstruction from non-central panoramas.