641 citations · 3k across the 58 of their papers we have counts for
79 papers · 1 filter
Tracking by 3D Model Estimation of Unknown Objects in Videos
Denys Rozumnyi, Jiri Matas, Marc Pollefeys +2
Most model-free visual object tracking methods formulate the tracking task as object location estimation given by a 2D segmentation or a bounding box in each video frame. We argue…
Planar Object Tracking via Weighted Optical Flow
Jonas Serych, Jiri Matas
We propose WOFT -- a novel method for planar object tracking that estimates a full 8 degrees-of-freedom pose, i.e. the homography w.r.t. a reference view. The method uses a novel m…
Human keypoint detection for close proximity human-robot interaction
Jan Docekal, Jakub Rozlivek, Jiri Matas +1
We study the performance of state-of-the-art human keypoint detectors in the context of close proximity human-robot interaction. The detection in this scenario is specific in that…
A Discriminative Single-Shot Segmentation Network for Visual Object Tracking
Alan Lukežič, Jiří Matas, Matej Kristan
Template-based discriminative trackers are currently the dominant tracking paradigm due to their robustness, but are restricted to bounding box tracking and a limited range of tran…
Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook
Sajid Javed, Martin Danelljan, Fahad Shahbaz Khan +3
Accurate and robust visual object tracking is one of the most challenging and fundamental computer vision problems. It entails estimating the trajectory of the target in an image s…
Point Cloud Color Constancy
Xiaoyan Xing, Yanlin Qian, Sibo Feng +2
In this paper, we present Point Cloud Color Constancy, in short PCCC, an illumination chromaticity estimation algorithm exploiting a point cloud. We leverage the depth information…
Lightweight Monocular Depth with a Novel Neural Architecture Search Method
Lam Huynh, Phong Nguyen, Jiri Matas +2
This paper presents a novel neural architecture search method, called LiDNAS, for generating lightweight monocular depth estimation models. Unlike previous neural architecture sear…
Monocular Depth Estimation Primed by Salient Point Detection and Normalized Hessian Loss
Lam Huynh, Matteo Pedone, Phong Nguyen +3
Deep neural networks have recently thrived on single image depth estimation. That being said, current developments on this topic highlight an apparent compromise between accuracy a…
Recall@k Surrogate Loss with Large Batches and Similarity Mixup
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 appro…
The Hitchhiker's Guide to Prior-Shift Adaptation
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. In the case of such prior shift, classifiers must be adapted c…
VSAC: Efficient and Accurate Estimator for H and F
Maksym Ivashechkin, Daniel Barath, Jiri Matas
We present VSAC, a RANSAC-type robust estimator with a number of novelties. It benefits from the introduction of the concept of independent inliers that improves significantly the…
USACv20: robust essential, fundamental and homography matrix estimation
Maksym Ivashechkin, Daniel Barath, Jiri Matas
We review the most recent RANSAC-like hypothesize-and-verify robust estimators. The best performing ones are combined to create a state-of-the-art version of the Universal Sample C…
Danish Fungi 2020 -- Not Just Another Image Recognition Dataset
Lukáš Picek, Milan Šulc, Jiří Matas +4
We introduce a novel fine-grained dataset and benchmark, the Danish Fungi 2020 (DF20). The dataset, constructed from observations submitted to the Atlas of Danish Fungi, is unique…
FEDS -- Filtered Edit Distance Surrogate
Yash Patel, Jiri Matas
This paper proposes a procedure to train a scene text recognition model using a robust learned surrogate of edit distance. The proposed method borrows from self-paced learning and…
Boosting Monocular Depth Estimation with Lightweight 3D Point Fusion
Lam Huynh, Phong Nguyen-Ha, Jiri Matas +2
In this paper, we propose enhancing monocular depth estimation by adding 3D points as depth guidance. Unlike existing depth completion methods, our approach performs well on extrem…
FMODetect: Robust Detection of Fast Moving Objects
Denys Rozumnyi, Jiri Matas, Filip Sroubek +2
We propose the first learning-based approach for fast moving objects detection. Such objects are highly blurred and move over large distances within one video frame. Fast moving ob…
DeFMO: Deblurring and Shape Recovery of Fast Moving Objects
Denys Rozumnyi, Martin R. Oswald, Vittorio Ferrari +2
Objects moving at high speed appear significantly blurred when captured with cameras. The blurry appearance is especially ambiguous when the object has complex shape or texture. In…
Efficient Initial Pose-graph Generation for Global SfM
Daniel Barath, Dmytro Mishkin, Ivan Eichhardt +2
We propose ways to speed up the initial pose-graph generation for global Structure-from-Motion algorithms. To avoid forming tentative point correspondences by FLANN and geometric v…
Fast Fourier Intrinsic Network
Yanlin Qian, Miaojing Shi, Joni-Kristian Kämäräinen +1
We address the problem of decomposing an image into albedo and shading. We propose the Fast Fourier Intrinsic Network, FFI-Net in short, that operates in the spectral domain, split…
RGBD-Net: Predicting color and depth images for novel views synthesis
Phong Nguyen-Ha, Animesh Karnewar, Lam Huynh +3
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 g…
BOP Challenge 2020 on 6D Object Localization
Tomas Hodan, Martin Sundermeyer, Bertram Drost +5
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…
Text Recognition -- Real World Data and Where to Find Them
Klára Janoušková, Jiri Matas, Lluis Gomez +1
We present a method for exploiting weakly annotated images to improve text extraction pipelines. The approach uses an arbitrary end-to-end text recognition system to obtain text re…
Learning Surrogates via Deep Embedding
Yash Patel, Tomas Hodan, Jiri Matas
This paper proposes a technique for training a neural network by minimizing a surrogate loss that approximates the target evaluation metric, which may be non-differentiable. The su…
Guiding Monocular Depth Estimation Using Depth-Attention Volume
Lam Huynh, Phong Nguyen-Ha, Jiri Matas +2
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 inte…