Viktor Kocur

Implementation for paper: "Detection of 3D bounding boxes of vehicles using perspective transformation for accurate speed measurement"

This repository contains the code for the paper "Traffic Camera Calibration via Vehicle Vanishing Point Detection" (ICANN 2021)

[CVPR 2024] Robust Self-calibration of Focal Lengths from the Fundamental Matrix

Materiály k výuke na FMFI.

[ICCV 2025 Oral] RePoseD: Efficient Relative Pose Estimation With Known Depth Information

No description.

Convert LaTeX Beamer slides to PowerPoint with flawless vector graphics and embedded video support.

A command-line tool that converts LaTeX Beamer slide presentations into PowerPoint files, turning overlay animations into separate slides and transferring embedded videos as native PowerPoint video shapes.

[ECCVW 2024] Are Minimal Radial Distortion Solvers Necessary for Relative Pose Estimation?

[CVPR 2025] Three-view Focal Length Recovery From Homographies

No description.

No description.

[CVPR 2025] Practical solutions to the relative pose of three calibrated cameras

Results for the paper "Detection of 3D Bounding Boxes of Vehicles Using Perspective Transformation for Accurate Speed Measurement"

No description.

Published results of CVWW 2019 Paper "Perspective transformation for accurate detection of 3D bounding boxes of vehicles in traffic surveillance"

[ICCV 2025] RePoseD: Efficient Relative Pose Estimation With Known Depth Information - PoseLib impelementation of the evaluated solvers

No description.

Minimal solvers for calibrated camera pose estimation

[CVPR 2026] InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields

No description.

[CVPR 2025] UniK3D: Universal Camera Monocular 3D Estimation

Expressive Body Capture: 3D Hands, Face, and Body from a Single Image

Code for the evaluation of Gaze Estimation networks using the NICO robotic platform

[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors

Official implementation of the solvers and estimators proposed in the paper "Relative Pose Estimation through Affine Corrections of Monocular Depth Priors"

Repository for issues with the Android UriTrack app

Beamer presentation template for FMPH, UKBA

No description.

No description.

Open Source Computer Vision Library

Code for "VSAC: Efficient and Accurate Estimator for H and F"

The MAGSAC algorithm for robust model fitting without using an inlier-outlier threshold

The Graph-Cut RANSAC algorithm proposed in paper: Daniel Barath and Jiri Matas; Graph-Cut RANSAC, Conference on Computer Vision and Pattern Recognition, 2018. It is available at http://openaccess.thecvf.com/content_cvpr_2018/papers/Barath_Graph-Cut_RANSAC_CVPR_2018_paper.pdf

Advanced RANSAC (DEGENSAC) with bells and whistles for H and F estimation

Code for "OnePose: One-Shot Object Pose Estimation without CAD Models", CVPR 2022

Simultaneous object detection and tracking using center points.

No description.

DTI Sprites

Code for BrnoCompSpeed dataset

Single view depth image based hand detection and pose estimation.