research
∙
07/09/2023
Reducing False Alarms in Video Surveillance by Deep Feature Statistical Modeling
Detecting relevant changes is a fundamental problem of video surveillanc...
share
research
∙
07/04/2023
Optimal and Efficient Binary Questioning for Human-in-the-Loop Annotation
Even though data annotation is extremely important for interpretability,...
research
∙
05/25/2023
Collaborative Blind Image Deblurring
Blurry images usually exhibit similar blur at various locations across t...
research
∙
05/25/2023
SING: A Plug-and-Play DNN Learning Technique
We propose SING (StabIlized and Normalized Gradient), a plug-and-play te...
research
∙
12/27/2022
Scaling Painting Style Transfer
Neural style transfer is a deep learning technique that produces an unpr...
research
∙
11/07/2022
Can neural networks extrapolate? Discussion of a theorem by Pedro Domingos
Neural networks trained on large datasets by minimizing a loss have beco...
research
∙
08/01/2022
Fast Two-step Blind Optical Aberration Correction
The optics of any camera degrades the sharpness of photographs, which is...
research
∙
04/23/2022
Investigating Neural Architectures by Synthetic Dataset Design
Recent years have seen the emergence of many new neural network structur...
research
∙
02/26/2021
Robust Rational Polynomial Camera Modelling for SAR and Pushbroom Imaging
The Rational Polynomial Camera (RPC) model can be used to describe a var...
research
∙
09/14/2020
Residual Learning for Effective joint Demosaicing-Denoising
Image demosaicing and denoising are key steps for color image production...
research
∙
07/23/2020
Silhouette Vectorization by Affine Scale-space
Silhouettes or 2D planar shapes are extremely important in human communi...
research
∙
04/24/2020
A Review of an Old Dilemma: Demosaicking First, or Denoising First?
Image denoising and demosaicking are the most important early stages in ...
research
∙
04/25/2019
Reducing Anomaly Detection in Images to Detection in Noise
Anomaly detectors address the difficult problem of detecting automatical...
research
∙
11/30/2018
Model-blind Video Denoising Via Frame-to-frame Training
Modeling the processing chain that has produced a video is a difficult r...
research
∙
11/30/2018
Non-Local Video Denoising by CNN
Non-local patch based methods were until recently state-of-the-art for i...
research
∙
08/28/2018
Quantitative Evaluation of Base and Detail Decomposition Filters Based on their Artifacts
This paper introduces a quantitative evaluation of filters that seek to ...
research
∙
08/07/2018
Image Anomalies: a Review and Synthesis of Detection Methods
We review the broad variety of methods that have been proposed for anoma...
research
∙
05/25/2018
Psychophysics, Gestalts and Games
Many psychophysical studies are dedicated to the evaluation of the human...
research
∙
07/22/2017
A survey of exemplar-based texture synthesis
Exemplar-based texture synthesis is the process of generating, from an i...
research
∙
01/19/2017
Accurate Motion Estimation through Random Sample Aggregated Consensus
We reconsider the classic problem of estimating accurately a 2D transfor...
research
∙
03/18/2016
From line segments to more organized Gestalts
In this paper, we reconsider the early computer vision bottom-up program...
research
∙
11/26/2015
An analysis of the factors affecting keypoint stability in scale-space
The most popular image matching algorithm SIFT, introduced by D. Lowe a ...
research
∙
09/08/2014
Comparing Feature Detectors: A bias in the repeatability criteria, and how to correct it
Most computer vision application rely on algorithms finding local corres...
research
∙
12/22/2012
High-precision camera distortion measurements with a "calibration harp"
This paper addresses the high precision measurement of the distortion of...
research
∙
12/06/2011