641 citations · 3k across the 58 of their papers we have counts for
14 papers · 2 filters
Object Tracking by Reconstruction with View-Specific Discriminative Correlation Filters
Ugur Kart, Alan Lukezic, Matej Kristan +2
Standard RGB-D trackers treat the target as an inherently 2D structure, which makes modelling appearance changes related even to simple out-of-plane rotation highly challenging. We…
Gyroscope-Aided Motion Deblurring with Deep Networks
Janne Mustaniemi, Juho Kannala, Simo Särkkä +2
We propose a deblurring method that incorporates gyroscope measurements into a convolutional neural network (CNN). With the help of such measurements, it can handle extremely stron…
Continual Occlusions and Optical Flow Estimation
Michal Neoral, Jan Šochman, Jiří Matas
Two optical flow estimation problems are addressed: i) occlusion estimation and handling, and ii) estimation from image sequences longer than two frames. The proposed ContinualFlow…
LSD -- Joint Denoising and Deblurring of Short and Long Exposure Images with CNNs
Janne Mustaniemi, Juho Kannala, Jiri Matas +2
The paper addresses the problem of acquiring high-quality photographs with handheld smartphone cameras in low-light imaging conditions. We propose an approach based on capturing pa…
A Summary of the 4th International Workshop on Recovering 6D Object Pose
Tomas Hodan, Rigas Kouskouridas, Tae-Kyun Kim +12
This document summarizes the 4th International Workshop on Recovering 6D Object Pose which was organized in conjunction with ECCV 2018 in Munich. The workshop featured four invited…
BOP: Benchmark for 6D Object Pose Estimation
Tomas Hodan, Frank Michel, Eric Brachmann +13
We propose a benchmark for 6D pose estimation of a rigid object from a single RGB-D input image. The training data consists of a texture-mapped 3D object model or images of the obj…
Performance Analysis and Robustification of Single-query 6-DoF Camera Pose Estimation
Junsheng Fu, Said Pertuz, Jiri Matas +1
We consider a single-query 6-DoF camera pose estimation with reference images and a point cloud, i.e. the problem of estimating the position and orientation of a camera by using re…
Fast Motion Deblurring for Feature Detection and Matching Using Inertial Measurements
Janne Mustaniemi, Juho Kannala, Simo Särkkä +2
Many computer vision and image processing applications rely on local features. It is well-known that motion blur decreases the performance of traditional feature detectors and desc…
Improving CNN classifiers by estimating test-time priors
Milan Sulc, Jiri Matas
The problem of different training and test set class priors is addressed in the context of CNN classifiers. We compare two different approaches to estimating the new priors: an exi…
Now you see me: evaluating performance in long-term visual tracking
Alan Lukežič, Luka Čehovin Zajc, Tomáš Vojíř +2
We propose a new long-term tracking performance evaluation methodology and present a new challenging dataset of carefully selected sequences with many target disappearances. We per…
Revisiting Gray Pixel for Statistical Illumination Estimation
Yanlin Qian, Said Pertuz, Jarno Nikkanen +2
We present a statistical color constancy method that relies on novel gray pixel detection and mean shift clustering. The method, called Mean Shifted Grey Pixel -- MSGP, is based on…
MAGSAC: marginalizing sample consensus
Daniel Barath, Jana Noskova, Jiri Matas
A method called, sigma-consensus, is proposed to eliminate the need for a user-defined inlier-outlier threshold in RANSAC. Instead of estimating the noise sigma, it is marginalized…
Depth Masked Discriminative Correlation Filter
Uğur Kart, Joni-Kristian Kämäräinen, Jiří Matas +2
Depth information provides a strong cue for occlusion detection and handling, but has been largely omitted in generic object tracking until recently due to lack of suitable benchma…
E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Text
Michal Bušta, Yash Patel, Jiri Matas
An end-to-end trainable (fully differentiable) method for multi-language scene text localization and recognition is proposed. The approach is based on a single fully convolutional…