Search Results for author:
Found 21 papers, 11 papers with code
Influence of field of view in visual prostheses design: Analysis with a VR system
In this work, we evaluate the influence of field of view with respect to spatial resolution in visual prostheses, measuring the accuracy and response time in a search and recognition task.
Scaled 360 layouts: Revisiting non-central panoramas
In this work we present a novel approach for 3D layout recovery of indoor environments using single non-central panoramas.
Visual Gyroscope: Combination of Deep Learning Features and Direct Alignment for Panoramic Stabilization
In this article we present a visual gyroscope based on equirectangular panoramas.
Convolution kernel adaptation to calibrated fisheye
Convolution kernels are the basic structural component of convolutional neural networks (CNNs).
Non-central panorama indoor dataset
Omnidirectional images are one of the main sources of information for learning based scene understanding algorithms.
Floor extraction and door detection for visually impaired guidance
In this work it is proposed a combination of sensors and algorithms that can lead to the building of a navigation system for visually impaired people.
Atlanta Scaled layouts from non-central panoramas
Our new pipeline aims to extract the boundaries of the structural lines of an indoor environment with a neural network and exploit the properties of non-central projection systems in a new geometrical processing to recover an scaled 3D layout.
OmniSCV: An Omnidirectional Synthetic Image Generator for Computer Vision
In this paper, we present a tool for generating datasets of omnidirectional images with semantic and depth information.
Multi-label affordance mapping from egocentric vision
We use this method to build the largest and most complete dataset on affordances based on the EPIC-Kitchen dataset, EPIC-Aff, which provides interaction-grounded, multi-label, metric and spatial affordance annotations.
Bayesian Deep Learning for Affordance Segmentation in images
We present a novel Bayesian deep network to detect affordances in images, at the same time that we quantify the distribution of the aleatoric and epistemic variance at the spatial level.
FreDSNet: Joint Monocular Depth and Semantic Segmentation with Fast Fourier Convolutions
Our experiments show that FreDSNet has similar performance as specific state of the art methods for semantic segmentation and depth estimation.
Ranked #2 on
Depth Estimation
on Stanford2D3D Panoramic
Assessing visual acuity in visual prostheses through a virtual-reality system
The development of new artificial vision simulation systems can be useful to guide the development of new visual devices and the optimization of field of view and resolution to provide a helpful and valuable visual aid to profoundly or totally blind patients.
Semantic Pose Verification for Outdoor Visual Localization with Self-supervised Contrastive Learning
Since semantic content is more robust to such changes, we exploit semantic information to improve visual localization.
Augmented reality navigation system for visual prosthesis
In this work, we propose an augmented reality navigation system for visual prosthesis that incorporates a software of reactive navigation and path planning which guides the subject through convenient, obstacle-free route.
Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Sets
This paper aims at learning category-specific 3D keypoints, in an unsupervised manner, using a collection of misaligned 3D point clouds of objects from an unknown category.
What's in my Room? Object Recognition on Indoor Panoramic Images
In the last few years, there has been a growing interest in taking advantage of the 360 panoramic images potential, while managing the new challenges they imply.
Corners for Layout: End-to-End Layout Recovery from 360 Images
The problem of 3D layout recovery in indoor scenes has been a core research topic for over a decade.
Semantic and structural image segmentation for prosthetic vision
Prosthetic vision is being applied to partially recover the retinal stimulation of visually impaired people.
PanoRoom: From the Sphere to the 3D Layout
We outperform the state of the art not only in accuracy of the 3D models but also in speed.
RGBiD-SLAM for Accurate Real-time Localisation and 3D Mapping
The presented approach is a dense direct SLAM method with the main characteristic of working with the depth maps in inverse depth parametrisation for the routines of dense alignment or keyframe fusion.
Layouts from Panoramic Images with Geometry and Deep Learning
In this paper, we propose a novel procedure for 3D layout recovery of indoor scenes from single 360 degrees panoramic images.
