8 citations · 18 across the 10 of their papers we have counts for
11 papers
Multi-task learning on partially labeled datasets via invariant/equivariant semi-supervised learning
Miquel Martí i Rabadán, Alessandro Pieropan, Hossein Azizpour +1
We investigate the potential of invariant and equivariant semi-supervised learning for addressing the challenges of training multi-task models on partially labeled datasets with di…
Visible Structure Retrieval for Lightweight Image-Based Relocalisation
Fereidoon Zangeneh, Leonard Bruns, Amit Dekel +2
Accurate camera pose estimation from an image observation in a previously mapped environment is commonly done through structure-based methods: by finding correspondences between 2D…
Quantifying Epistemic Uncertainty in Absolute Pose Regression
Fereidoon Zangeneh, Amit Dekel, Alessandro Pieropan +1
Visual relocalization is the task of estimating the camera pose given an image it views. Absolute pose regression offers a solution to this task by training a neural network, direc…
Conditional Variational Autoencoders for Probabilistic Pose Regression
Fereidoon Zangeneh, Leonard Bruns, Amit Dekel +2
Robots rely on visual relocalization to estimate their pose from camera images when they lose track. One of the challenges in visual relocalization is repetitive structures in the…
A Probabilistic Framework for Visual Localization in Ambiguous Scenes
Fereidoon Zangeneh, Leonard Bruns, Amit Dekel +2
Visual localization allows autonomous robots to relocalize when losing track of their pose by matching their current observation with past ones. However, ambiguous scenes pose a ch…
Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks
Miquel Martí i Rabadán, Alessandro Pieropan, Hossein Azizpour +1
We propose Dense FixMatch, a simple method for online semi-supervised learning of dense and structured prediction tasks combining pseudo-labeling and consistency regularization via…
An analysis of over-sampling labeled data in semi-supervised learning with FixMatch
Miquel Martí i Rabadán, Sebastian Bujwid, Alessandro Pieropan +2
Most semi-supervised learning methods over-sample labeled data when constructing training mini-batches. This paper studies whether this common practice improves learning and how. W…
Real-Time Semantic Stereo Matching
Pier Luigi Dovesi, Matteo Poggi, Lorenzo Andraghetti +4
Scene understanding is paramount in robotics, self-navigation, augmented reality, and many other fields. To fully accomplish this task, an autonomous agent has to infer the 3D stru…
Enhancing self-supervised monocular depth estimation with traditional visual odometry
Lorenzo Andraghetti, Panteleimon Myriokefalitakis, Pier Luigi Dovesi +4
Estimating depth from a single image represents an attractive alternative to more traditional approaches leveraging multiple cameras. In this field, deep learning yielded outstandi…
GANtruth - an unpaired image-to-image translation method for driving scenarios
Sebastian Bujwid, Miquel Martí, Hossein Azizpour +1
Synthetic image translation has significant potentials in autonomous transportation systems. That is due to the expense of data collection and annotation as well as the unmanageabl…
Feature Descriptors for Tracking by Detection: a Benchmark
Alessandro Pieropan, Mårten Björkman, Niklas Bergström +1
In this paper, we provide an extensive evaluation of the performance of local descriptors for tracking applications. Many different descriptors have been proposed in the literature…