This project aims to estimate camera pose using homography for a given video. Steps involved are designing an image processing pipeline to extract paper's corners, computing homography between real-world points and pixel coordinates of the corners, and decomposing the homography matrix to obtain rotation and translation parameters.

perform camera pose estimation using homography

Novel approach to estimating the pair-wise relationship between nearby cameras using fiducial markers. It then performs a full optimization incorporating real-world information to refine the results further.

A mobile observer samples sequences of narrow-field projections of configurations in ambient space. For rigid transformations, a unique metrical reconstruction is known to be possible from three orthographic views of four points.

Render an 3d Object

Depth Estimation Using Stereo Cameras

Camera Pose Estimation using DELF

[WACV2022] "Shape-Coded ArUco: Fiducial Marker for Bridging 2D and 3D Modalities".

Series of experiments to calculate the real world coordinates of the camera using static images

Python code to estimate depth using stereo vision.

A CNN based Depth, Optical Flow, Flow Uncertainty and Camera Pose Prediction pipeline

Datasets for long-term visual localization with sequential images in large-scale spaces

SoccerNet@CVPR | 1st place solution for Camera Calibration Challenge 2023

[ICRA'20] Robust 360-8PA": Redesigning The Normalized 8-point Algorithm for 360-FoV Images

Given a map data (image + lidar), estimate the 6 DoF camera pose of the query image.

This demo uses a deep neural network and two generic cameras to perform 3D pose estimation.

A Deep Learning Approach to Camera Pose Estimation

[CVPR 2023] Two-view Geometry Scoring Without Correspondences

Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimation (CVPR 2021)