1.9k citations · 1.9k across the 10 of their papers we have counts for
11 papers
3D Structure from 2D Microscopy images using Deep Learning
Benjamin J. Blundell, Christian Sieben, Suliana Manley +3
Understanding the structure of a protein complex is crucial indetermining its function. However, retrieving accurate 3D structures from microscopy images is highly challenging, par…
Progressive Batching for Efficient Non-linear Least Squares
Huu Le, Christopher Zach, Edward Rosten +1
Non-linear least squares solvers are used across a broad range of offline and real-time model fitting problems. Most improvements of the basic Gauss-Newton algorithm tackle converg…
Large Scale Photometric Bundle Adjustment
Oliver J. Woodford, Edward Rosten
Direct methods have shown promise on visual odometry and SLAM, leading to greater accuracy and robustness over feature-based methods. However, offline 3-d reconstruction from inter…
Y-Autoencoders: disentangling latent representations via sequential-encoding
Massimiliano Patacchiola, Patrick Fox-Roberts, Edward Rosten
In the last few years there have been important advancements in generative models with the two dominant approaches being Generative Adversarial Networks (GANs) and Variational Auto…
Improved RANSAC performance using simple, iterative minimal-set solvers
Edward Rosten, Gerhard Reitmayr, Tom Drummond
RANSAC is a popular technique for estimating model parameters in the presence of outliers. The best speed is achieved when the minimum possible number of points is used to estimate…
Automatic creation of urban velocity fields from aerial video
Edward Rosten, Rohan Loveland, Mark Hickman
In this paper, we present a system for modelling vehicle motion in an urban scene from low frame-rate aerial video. In particular, the scene is modelled as a probability distributi…