Search Results for author: Jiri Matas

Found 74 papers, 34 papers with code

Deep MAGSAC++

no code implementations28 Nov 2021 Wei Tong, Jiri Matas, Daniel Barath

We propose Deep MAGSAC++ combining the advantages of traditional and deep robust estimators.

Point Cloud Color Constancy

no code implementations22 Nov 2021 Xiaoyan Xing, Yanlin Qian, Sibo Feng, Yuhan Dong, Jiri Matas

In this paper, we present Point Cloud Color Constancy, in short PCCC, an illumination chromaticity estimation algorithm exploiting a point cloud.

Color Constancy

Recall@k Surrogate Loss with Large Batches and Similarity Mixup

2 code implementations25 Aug 2021 Yash Patel, Giorgos Tolias, Jiri Matas

This work focuses on learning deep visual representation models for retrieval by exploring the interplay between a new loss function, the batch size, and a new regularization approach.

Image Retrieval Metric Learning +1

Monocular Depth Estimation Primed by Salient Point Detection and Normalized Hessian Loss

no code implementations25 Aug 2021 Lam Huynh, Matteo Pedone, Phong Nguyen, Jiri Matas, Esa Rahtu, Janne Heikkila

In addition, we introduce a normalized Hessian loss term invariant to scaling and shear along the depth direction, which is shown to substantially improve the accuracy.

Monocular Depth Estimation

Lightweight Monocular Depth with a Novel Neural Architecture Search Method

no code implementations25 Aug 2021 Lam Huynh, Phong Nguyen, Jiri Matas, Esa Rahtu, Janne Heikkila

This paper presents a novel neural architecture search method, called LiDNAS, for generating lightweight monocular depth estimation models.

Monocular Depth Estimation Neural Architecture Search

The Hitchhiker's Guide to Prior-Shift Adaptation

1 code implementation22 Jun 2021 Tomas Sipka, Milan Sulc, Jiri Matas

In many computer vision classification tasks, class priors at test time often differ from priors on the training set.

Classification Fine-Grained Image Classification

VSAC: Efficient and Accurate Estimator for H and F

no code implementations ICCV 2021 Maksym Ivashechkin, Daniel Barath, Jiri Matas

Experiments on four standard datasets show that VSAC is significantly faster than all its predecessors and runs on average in 1-2 ms, on a CPU.

USACv20: robust essential, fundamental and homography matrix estimation

no code implementations11 Apr 2021 Maksym Ivashechkin, Daniel Barath, Jiri Matas

We review the most recent RANSAC-like hypothesize-and-verify robust estimators.

Progressive-X+: Clustering in the Consensus Space

no code implementations25 Mar 2021 Daniel Barath, Denys Rozumny, Ivan Eichhardt, Levente Hajder, Jiri Matas

We propose Progressive-X+, a new algorithm for finding an unknown number of geometric models, e. g., homographies.

Pose Estimation

FEDS -- Filtered Edit Distance Surrogate

no code implementations8 Mar 2021 Yash Patel, Jiri Matas

This paper proposes a procedure to train a scene text recognition model using a robust learned surrogate of edit distance.

Scene Text Recognition

Road Anomaly Detection by Partial Image Reconstruction With Segmentation Coupling

no code implementations ICCV 2021 Tomas Vojir, Tomas Sipka, Rahaf Aljundi, Nikolay Chumerin, Daniel Olmeda Reino, Jiri Matas

To that end, we propose a reconstruction module that can be used with many existing semantic segmentation networks, and that is trained to recognize and reconstruct road (drivable) surface from a small bottleneck.

Anomaly Detection Autonomous Driving +2

FMODetect: Robust Detection of Fast Moving Objects

1 code implementation ICCV 2021 Denys Rozumnyi, Jiri Matas, Filip Sroubek, Marc Pollefeys, Martin R. Oswald

Compared to other methods, such as deblatting, the inference is of several orders of magnitude faster and allows applications such as real-time fast moving object detection and retrieval in large video collections.

Deblurring Frame +2

DeFMO: Deblurring and Shape Recovery of Fast Moving Objects

5 code implementations CVPR 2021 Denys Rozumnyi, Martin R. Oswald, Vittorio Ferrari, Jiri Matas, Marc Pollefeys

We propose a method that, given a single image with its estimated background, outputs the object's appearance and position in a series of sub-frames as if captured by a high-speed camera (i. e. temporal super-resolution).

Deblurring Object Tracking +1

RGBD-Net: Predicting color and depth images for novel views synthesis

no code implementations29 Nov 2020 Phong Nguyen, Animesh Karnewar, Lam Huynh, Esa Rahtu, Jiri Matas, Janne Heikkila

We propose a new cascaded architecture for novel view synthesis, called RGBD-Net, which consists of two core components: a hierarchical depth regression network and a depth-aware generator network.

Novel View Synthesis

Fast Fourier Intrinsic Network

no code implementations9 Nov 2020 Yanlin Qian, Miaojing Shi, Joni-Kristian Kämäräinen, Jiri Matas

We address the problem of decomposing an image into albedo and shading.

ArXiving Before Submission Helps Everyone

no code implementations11 Oct 2020 Dmytro Mishkin, Amy Tabb, Jiri Matas

We claim, and present evidence, that allowing arXiv publication before a conference or journal submission benefits researchers, especially early career, as well as the whole scientific community.

BOP Challenge 2020 on 6D Object Localization

3 code implementations15 Sep 2020 Tomas Hodan, Martin Sundermeyer, Bertram Drost, Yann Labbe, Eric Brachmann, Frank Michel, Carsten Rother, Jiri Matas

This paper presents the evaluation methodology, datasets, and results of the BOP Challenge 2020, the third in a series of public competitions organized with the goal to capture the status quo in the field of 6D object pose estimation from an RGB-D image.

6D Pose Estimation 6D Pose Estimation using RGB +3

Text Recognition -- Real World Data and Where to Find Them

no code implementations6 Jul 2020 Klára Janoušková, Jiri Matas, Lluis Gomez, Dimosthenis Karatzas

We present a method for exploiting weakly annotated images to improve text extraction pipelines.

Learning Surrogates via Deep Embedding

no code implementations ECCV 2020 Yash Patel, Tomas Hodan, Jiri Matas

The effectiveness of the proposed technique is demonstrated in a post-tuning setup, where a trained model is tuned using the learned surrogate.

Scene Text Recognition

Guiding Monocular Depth Estimation Using Depth-Attention Volume

2 code implementations ECCV 2020 Lam Huynh, Phong Nguyen-Ha, Jiri Matas, Esa Rahtu, Janne Heikkila

Recovering the scene depth from a single image is an ill-posed problem that requires additional priors, often referred to as monocular depth cues, to disambiguate different 3D interpretations.

Monocular Depth Estimation

EPOS: Estimating 6D Pose of Objects with Symmetries

1 code implementation CVPR 2020 Tomas Hodan, Daniel Barath, Jiri Matas

A data-dependent number of corresponding 3D locations is selected per pixel, and poses of possibly multiple object instances are estimated using a robust and efficient variant of the PnP-RANSAC algorithm.

6D Pose Estimation 6D Pose Estimation using RGB +1

A Benchmark for Temporal Color Constancy

2 code implementations8 Mar 2020 Yanlin Qian, Jani Käpylä, Joni-Kristian Kämäräinen, Samu Koskinen, Jiri Matas

The conventional approach is to use a single frame - shot frame - to estimate the scene illumination color.

Color Constancy Frame

Image Matching across Wide Baselines: From Paper to Practice

5 code implementations3 Mar 2020 Yuhe Jin, Dmytro Mishkin, Anastasiia Mishchuk, Jiri Matas, Pascal Fua, Kwang Moo Yi, Eduard Trulls

We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task -- the accuracy of the reconstructed camera pose -- as our primary metric.

DAL -- A Deep Depth-aware Long-term Tracker

no code implementations2 Dec 2019 Yanlin Qian, Alan Lukežič, Matej Kristan, Joni-Kristian Kämäräinen, Jiri Matas

In this work, we propose a deep depth-aware long-term tracker that achieves state-of-the-art RGBD tracking performance and is fast to run.

Sub-frame Appearance and 6D Pose Estimation of Fast Moving Objects

2 code implementations CVPR 2020 Denys Rozumnyi, Jan Kotera, Filip Sroubek, Jiri Matas

We propose a novel method that tracks fast moving objects, mainly non-uniform spherical, in full 6 degrees of freedom, estimating simultaneously their 3D motion trajectory, 3D pose and object appearance changes with a time step that is a fraction of the video frame exposure time.

6D Pose Estimation Deblurring +4

Progressive-X: Efficient, Anytime, Multi-Model Fitting Algorithm

2 code implementations ICCV 2019 Daniel Barath, Jiri Matas

The Progressive-X algorithm, Prog-X in short, is proposed for geometric multi-model fitting.

Motion Segmentation

Progressive NAPSAC: sampling from gradually growing neighborhoods

no code implementations5 Jun 2019 Daniel Barath, Maksym Ivashechkin, Jiri Matas

We propose Progressive NAPSAC, P-NAPSAC in short, which merges the advantages of local and global sampling by drawing samples from gradually growing neighborhoods.

Rolling Shutter Camera Synchronization with Sub-millisecond Accuracy

1 code implementation28 Feb 2019 Matej Smid, Jiri Matas

A simple method for synchronization of video streams with a precision better than one millisecond is proposed.

Frame Video Synchronization

Flash Lightens Gray Pixels

no code implementations27 Feb 2019 Yanlin Qian, Song Yan, Joni-Kristian Kämäräinen, Jiri Matas

In the real world, a scene is usually cast by multiple illuminants and herein we address the problem of spatial illumination estimation.

On Finding Gray Pixels

2 code implementations CVPR 2019 Yanlin Qian, Joni-Kristian Kämäräinen, Jarno Nikkanen, Jiri Matas

We propose a novel grayness index for finding gray pixels and demonstrate its effectiveness and efficiency in illumination estimation.

Object Tracking by Reconstruction with View-Specific Discriminative Correlation Filters

no code implementations CVPR 2019 Ugur Kart, Alan Lukezic, Matej Kristan, Joni-Kristian Kamarainen, Jiri Matas

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.

3D Reconstruction Object Tracking

LSD$_2$ -- Joint Denoising and Deblurring of Short and Long Exposure Images with CNNs

no code implementations23 Nov 2018 Janne Mustaniemi, Juho Kannala, Jiri Matas, Simo Särkkä, Janne Heikkilä

The paper addresses the problem of acquiring high-quality photographs with handheld smartphone cameras in low-light imaging conditions.

Deblurring Denoising

Gyroscope-Aided Motion Deblurring with Deep Networks

1 code implementation1 Oct 2018 Janne Mustaniemi, Juho Kannala, Simo Särkkä, Jiri Matas, Janne Heikkilä

We propose a deblurring method that incorporates gyroscope measurements into a convolutional neural network (CNN).

Deblurring

Performance Analysis and Robustification of Single-query 6-DoF Camera Pose Estimation

no code implementations17 Aug 2018 Junsheng Fu, Said Pertuz, Jiri Matas, Joni-Kristian Kämäräinen

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 reference images and a point cloud.

Pose Estimation

Fast Motion Deblurring for Feature Detection and Matching Using Inertial Measurements

no code implementations22 May 2018 Janne Mustaniemi, Juho Kannala, Simo Särkkä, Jiri Matas, Janne Heikkilä

It is well-known that motion blur decreases the performance of traditional feature detectors and descriptors.

Deblurring

Improving CNN classifiers by estimating test-time priors

no code implementations21 May 2018 Milan Sulc, Jiri Matas

The proposed Maximum a Posteriori estimation increases the prediction accuracy by 2. 8% on PlantCLEF 2017 and by 1. 8% on FGVCx Fungi, where the existing MLE method would lead to a decrease accuracy.

Image Classification

Revisiting Gray Pixel for Statistical Illumination Estimation

1 code implementation22 Mar 2018 Yanlin Qian, Said Pertuz, Jarno Nikkanen, Joni-Kristian Kämäräinen, Jiri Matas

We present a statistical color constancy method that relies on novel gray pixel detection and mean shift clustering.

Color Constancy

MAGSAC: marginalizing sample consensus

2 code implementations CVPR 2019 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.

Homography Estimation

E2E-MLT - an Unconstrained End-to-End Method for Multi-Language Scene Text

2 code implementations30 Jan 2018 Michal Bušta, Yash Patel, Jiri Matas

An end-to-end trainable (fully differentiable) method for multi-language scene text localization and recognition is proposed.

Optical Character Recognition

DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks

12 code implementations CVPR 2018 Orest Kupyn, Volodymyr Budzan, Mykola Mykhailych, Dmytro Mishkin, Jiri Matas

The quality of the deblurring model is also evaluated in a novel way on a real-world problem -- object detection on (de-)blurred images.

Deblurring Object Detection

Recurrent Color Constancy

no code implementations ICCV 2017 Yanlin Qian, Ke Chen, Jarno Nikkanen, Joni-Kristian Kamarainen, Jiri Matas

We introduce a novel formulation of temporal color constancy which considers multiple frames preceding the frame for which illumination is estimated.

Color Constancy Frame

Graph-Cut RANSAC

1 code implementation CVPR 2018 Daniel Barath, Jiri Matas

A novel method for robust estimation, called Graph-Cut RANSAC, GC-RANSAC in short, is introduced.

Multi-Class Model Fitting by Energy Minimization and Mode-Seeking

1 code implementation ECCV 2018 Daniel Barath, Jiri Matas

The move replaces a set of labels with the corresponding density mode in the model parameter domain, thus achieving fast and robust optimization.

Motion Detection Motion Segmentation

Inertial-Based Scale Estimation for Structure from Motion on Mobile Devices

1 code implementation29 Nov 2016 Janne Mustaniemi, Juho Kannala, Simo Särkkä, Jiri Matas, Janne Heikkilä

In the process, we also perform a temporal and spatial alignment of the camera and the IMU.

The World of Fast Moving Objects

3 code implementations CVPR 2017 Denys Rozumnyi, Jan Kotera, Filip Sroubek, Lukas Novotny, Jiri Matas

The notion of a Fast Moving Object (FMO), i. e. an object that moves over a distance exceeding its size within the exposure time, is introduced.

Frame Super-Resolution

In the Saddle: Chasing Fast and Repeatable Features

1 code implementation24 Aug 2016 Javier Aldana-Iuit, Dmytro Mishkin, Ondrej Chum, Jiri Matas

A novel similarity-covariant feature detector that extracts points whose neighbourhoods, when treated as a 3D intensity surface, have a saddle-like intensity profile.

Deep Structured-Output Regression Learning for Computational Color Constancy

no code implementations13 Jul 2016 Yanlin Qian, Ke Chen, Joni-Kristian Kamarainen, Jarno Nikkanen, Jiri Matas

Computational color constancy that requires esti- mation of illuminant colors of images is a fundamental yet active problem in computer vision, which can be formulated into a regression problem.

Color Constancy

Systematic evaluation of CNN advances on the ImageNet

1 code implementation7 Jun 2016 Dmytro Mishkin, Nikolay Sergievskiy, Jiri Matas

The paper systematically studies the impact of a range of recent advances in CNN architectures and learning methods on the object categorization (ILSVRC) problem.

Object Categorization

From Dusk Till Dawn: Modeling in the Dark

no code implementations CVPR 2016 Filip Radenovic, Johannes L. Schonberger, Dinghuang Ji, Jan-Michael Frahm, Ondrej Chum, Jiri Matas

We present an algorithm that leverages the appearance variety to obtain more complete and accurate scene geometry along with consistent multi-illumination appearance information.

FASText: Efficient Unconstrained Scene Text Detector

no code implementations ICCV 2015 Michal Busta, Lukas Neumann, Jiri Matas

After a novel efficient classification step, the number of regions is reduced to 7 times less than the standard method and is still almost 3 times faster.

General Classification

All you need is a good init

8 code implementations ICLR 2015 Dmytro Mishkin, Jiri Matas

Experiment with different activation functions (maxout, ReLU-family, tanh) show that the proposed initialization leads to learning of very deep nets that (i) produces networks with test accuracy better or equal to standard methods and (ii) is at least as fast as the complex schemes proposed specifically for very deep nets such as FitNets (Romero et al. (2015)) and Highway (Srivastava et al. (2015)).

Image Classification

Cascaded Sparse Spatial Bins for Efficient and Effective Generic Object Detection

no code implementations ICCV 2015 David Novotny, Jiri Matas

The efficiency is achieved by the use of spatial bins in a novel combination with sparsity-inducing group normalized SVM.

Object Detection

WxBS: Wide Baseline Stereo Generalizations

2 code implementations24 Apr 2015 Dmytro Mishkin, Jiri Matas, Michal Perdoch, Karel Lenc

We have presented a new problem -- the wide multiple baseline stereo (WxBS) -- which considers matching of images that simultaneously differ in more than one image acquisition factor such as viewpoint, illumination, sensor type or where object appearance changes significantly, e. g. over time.

Online Adaptive Hidden Markov Model for Multi-Tracker Fusion

no code implementations23 Apr 2015 Tomas Vojir, Jiri Matas, Jana Noskova

We show the effectiveness of the proposed method on combination of two and three tracking algorithms.

Visual Object Tracking

MODS: Fast and Robust Method for Two-View Matching

2 code implementations9 Mar 2015 Dmytro Mishkin, Jiri Matas, Michal Perdoch

A novel algorithm for wide-baseline matching called MODS - Matching On Demand with view Synthesis - is presented.

Detection, Rectification and Segmentation of Coplanar Repeated Patterns

no code implementations CVPR 2014 James Pritts, Ondrej Chum, Jiri Matas

This paper presents a novel and general method for the detection, rectification and segmentation of imaged coplanar repeated patterns.

Detection of Partially Visible Objects

no code implementations24 Nov 2013 Patrick Ott, Mark Everingham, Jiri Matas

An "elephant in the room" for most current object detection and localization methods is the lack of explicit modelling of partial visibility due to occlusion by other objects or truncation by the image boundary.

Object Detection

Two-View Matching with View Synthesis Revisited

no code implementations17 Jun 2013 Dmytro Mishkin, Michal Perdoch, Jiri Matas

Wide-baseline matching focussing on problems with extreme viewpoint change is considered.

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