Given 2D point correspondences between an image pair, inferring the camera motion is a
fundamental issue in the computer vision community. The existing works generally set out …

Camera motion estimation, such as relative pose estimation and absolute pose estimation,
are fundamental problems in computer vision and robotics. To obtain the motion parameters …

Instantaneous camera motion estimation is an important research topic in computer vision.
Although in theory more than five points uniquely determine the solution in an ideal …

This work addresses the generic problem of global motion estimation (homographies,
camera poses, orientations, etc.) from relative measurements in the presence of outliers. We …

A novel method is introduced for optimal estimation of rigid camera motion from
instantaneous velocity measurements. The error surface associated with this problem is …

In this letter, we consider the problem of recovering the rotation and translation changes of a
moving camera from captured images. This problem is traditionally solved using the epipolar …

We present a novel 2-point method for estimating the relative pose of a camera undergoing
planar motion from 3D data (eg from a calibrated stereo setup or an RGB-D sensor). Unlike …

We study the inverse problem of estimating n locations t_1,t_2,...,t_n (up to global scale,
translation, and negation) in R^d from noisy measurements of a subset of the (unsigned) …

A robust estimation method, Balanced Least Absolute Value Estimator (BLAVE), is
introduced and compared with the traditional RANdom SAmple Consensus (RANSAC) …

We propose simple and efficient methods for estimating the camera motion between two
images when this motion is small. While current solutions are still either slow, or unstable in …