Viktor Kocur

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

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

retinanet_traffic_3D. Implementation for paper: "Detection of 3D bounding boxes of vehicles using perspective transformation for accurate speed measurement"

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

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

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

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

depth2pose. Python

aicc. Python

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

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

rdnet. Python

DeepAFMReconstruction. Python

CVWW2019_results. Published results of CVWW 2019 Paper "Perspective transformation for accurate detection of 3D bounding boxes of vehicles in traffic surveillance"

edu. Materiály k výuke na FMFI.

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