Search Results for author: Aleš Leonardis

Found 14 papers, 4 papers with code

Wavelet-Based Dual-Branch Network for Image Demoiréing

no code implementations ECCV 2020 Lin Liu, Jianzhuang Liu, Shanxin Yuan, Gregory Slabaugh, Aleš Leonardis, Wengang Zhou, Qi Tian

When smartphone cameras are used to take photos of digital screens, usually moire patterns result, severely degrading photo quality.

Image Restoration Rain Removal

FlexHDR: Modelling Alignment and Exposure Uncertainties for Flexible HDR Imaging

no code implementations7 Jan 2022 Sibi Catley-Chandar, Thomas Tanay, Lucas Vandroux, Aleš Leonardis, Gregory Slabaugh, Eduardo Pérez-Pellitero

We introduce a strategy that learns to jointly align and assess the alignment and exposure reliability using an HDR-aware, uncertainty-driven attention map that robustly merges the frames into a single high quality HDR image.

DepthTrack : Unveiling the Power of RGBD Tracking

1 code implementation31 Aug 2021 Song Yan, Jinyu Yang, Jani Käpylä, Feng Zheng, Aleš Leonardis, Joni-Kristian Kämäräinen

RGBD (RGB plus depth) object tracking is gaining momentum as RGBD sensors have become popular in many application fields such as robotics. However, the best RGBD trackers are extensions of the state-of-the-art deep RGB trackers.

Object Tracking

NTIRE 2021 Challenge on High Dynamic Range Imaging: Dataset, Methods and Results

1 code implementation2 Jun 2021 Eduardo Pérez-Pellitero, Sibi Catley-Chandar, Aleš Leonardis, Radu Timofte

This paper reviews the first challenge on high-dynamic range (HDR) imaging that was part of the New Trends in Image Restoration and Enhancement (NTIRE) workshop, held in conjunction with CVPR 2021.

HDR Reconstruction Image Restoration

A Survey on Neural Network Interpretability

no code implementations28 Dec 2020 Yu Zhang, Peter Tiňo, Aleš Leonardis, Ke Tang

Along with the great success of deep neural networks, there is also growing concern about their black-box nature.

Drug Discovery

Assessing Capsule Networks With Biased Data

no code implementations9 Apr 2019 Bruno Ferrarini, Shoaib Ehsan, Adrien Bartoli, Aleš Leonardis, Klaus D. McDonald-Maier

This paper aims to fill this gap and proposes two experimental scenarios to assess the tolerance to imbalanced training data and to determine the generalization performance of a model with unfamiliar affine transformations of the images.

Spatially-Adaptive Filter Units for Deep Neural Networks

2 code implementations CVPR 2018 Domen Tabernik, Matej Kristan, Aleš Leonardis

Classical deep convolutional networks increase receptive field size by either gradual resolution reduction or application of hand-crafted dilated convolutions to prevent increase in the number of parameters.

Image Classification Semantic Segmentation

Beyond standard benchmarks: Parameterizing performance evaluation in visual object tracking

no code implementations ICCV 2017 Luka Čehovin Zajc, Alan Lukežič, Aleš Leonardis, Matej Kristan

Object-to-camera motion produces a variety of apparent motion patterns that significantly affect performance of short-term visual trackers.

Visual Object Tracking

Visual Stability Prediction and Its Application to Manipulation

no code implementations15 Sep 2016 Wenbin Li, Aleš Leonardis, Mario Fritz

We present a learning-based approach based on simulated data that predicts stability of towers comprised of wooden blocks under different conditions and quantities related to the potential fall of the towers.

Towards Deep Compositional Networks

no code implementations13 Sep 2016 Domen Tabernik, Matej Kristan, Jeremy L. Wyatt, Aleš Leonardis

We propose a novel analytic model of a basic unit in a layered hierarchical model with both explicit compositional structure and a well-defined discriminative cost function.

To Fall Or Not To Fall: A Visual Approach to Physical Stability Prediction

no code implementations31 Mar 2016 Wenbin Li, Seyedmajid Azimi, Aleš Leonardis, Mario Fritz

In this paper, we contrast a more traditional approach of taking a model-based route with explicit 3D representations and physical simulation by an end-to-end approach that directly predicts stability and related quantities from appearance.

Visual object tracking performance measures revisited

no code implementations20 Feb 2015 Luka Čehovin, Aleš Leonardis, Matej Kristan

The problem of visual tracking evaluation is sporting a large variety of performance measures, and largely suffers from lack of consensus about which measures should be used in experiments.

Visual Object Tracking Visual Tracking

Cannot find the paper you are looking for? You can Submit a new open access paper.