Search Results for author: Matthew Johnson

Found 15 papers, 4 papers with code

FastNeRF: High-Fidelity Neural Rendering at 200FPS

no code implementations ICCV 2021 Stephan J. Garbin, Marek Kowalski, Matthew Johnson, Jamie Shotton, Julien Valentin

Recent work on Neural Radiance Fields (NeRF) showed how neural networks can be used to encode complex 3D environments that can be rendered photorealistically from novel viewpoints.

Mixed Reality Neural Rendering

NDRIO White Paper: Envisioning Digital Research Infrastructure for the Simons Observatory

no code implementations22 Dec 2020 Adam D. Hincks, Simone Aiola, J. Richard Bond, Erminia Calabrese, Andrei Frolov, José Tomás Gálvez Ghersi, Renée Hložek, Matthew Johnson, Mathew S. Madhavacheril, Moritz Münchmeyer, Lyman A. Page, Jonathan Sievers, Suzanne T. Staggs, Alexander van Engelen

Observations of the cosmic microwave background (CMB) are an incredibly fertile source of information for studying the origins and evolution of the Universe.

Instrumentation and Methods for Astrophysics Cosmology and Nongalactic Astrophysics

Computing Weighted Subset Transversals in $H$-Free Graphs

no code implementations28 Jul 2020 Nick Brettell, Matthew Johnson, Daniel Paulusma

For the Odd Cycle Transversal problem, the task is to find a small set $S$ of vertices in a graph that intersects every cycle of odd length.

Data Structures and Algorithms Discrete Mathematics Combinatorics

A high fidelity synthetic face framework for computer vision

no code implementations16 Jul 2020 Tadas Baltrusaitis, Erroll Wood, Virginia Estellers, Charlie Hewitt, Sebastian Dziadzio, Marek Kowalski, Matthew Johnson, Thomas J. Cashman, Jamie Shotton

Analysis of faces is one of the core applications of computer vision, with tasks ranging from landmark alignment, head pose estimation, expression recognition, and face recognition among others.

Face Model Face Recognition +1

High Resolution Zero-Shot Domain Adaptation of Synthetically Rendered Face Images

no code implementations ECCV 2020 Stephan J. Garbin, Marek Kowalski, Matthew Johnson, Jamie Shotton

In contrast to computer graphics approaches, generative models learned from more readily available 2D image data have been shown to produce samples of human faces that are hard to distinguish from real data.

Domain Adaptation

CONFIG: Controllable Neural Face Image Generation

1 code implementation ECCV 2020 Marek Kowalski, Stephan J. Garbin, Virginia Estellers, Tadas Baltrušaitis, Matthew Johnson, Jamie Shotton

Our ability to sample realistic natural images, particularly faces, has advanced by leaps and bounds in recent years, yet our ability to exert fine-tuned control over the generative process has lagged behind.

Face Model Image Generation +1

Towards Automatic Screening of Typical and Atypical Behaviors in Children With Autism

no code implementations29 Jul 2019 Andrew Cook, Bappaditya Mandal, Donna Berry, Matthew Johnson

This paper has been withdrawn by the authors due to insufficient or definition error(s) in the ethics approval protocol.

Simple, Distributed, and Accelerated Probabilistic Programming

1 code implementation NeurIPS 2018 Dustin Tran, Matthew Hoffman, Dave Moore, Christopher Suter, Srinivas Vasudevan, Alexey Radul, Matthew Johnson, Rif A. Saurous

For both a state-of-the-art VAE on 64x64 ImageNet and Image Transformer on 256x256 CelebA-HQ, our approach achieves an optimal linear speedup from 1 to 256 TPUv2 chips.

Probabilistic Programming

Capturing Structure Implicitly from Time-Series having Limited Data

1 code implementation15 Mar 2018 Daniel Emaasit, Matthew Johnson

Most of the current literature in these fields involve visualizing the time-series for noticeable structure and hard coding them into pre-specified parametric functions.

Small Data Image Classification Time Series

The Segmented iHMM: A Simple, Efficient Hierarchical Infinite HMM

no code implementations20 Feb 2016 Ardavan Saeedi, Matthew Hoffman, Matthew Johnson, Ryan Adams

We propose the segmented iHMM (siHMM), a hierarchical infinite hidden Markov model (iHMM) that supports a simple, efficient inference scheme.

Time Series

Dependent Multinomial Models Made Easy: Stick-Breaking with the Polya-gamma Augmentation

no code implementations NeurIPS 2015 Scott Linderman, Matthew Johnson, Ryan P. Adams

For example, nucleotides in a DNA sequence, children's names in a given state and year, and text documents are all commonly modeled with multinomial distributions.

Bayesian Inference

Efficient non-greedy optimization of decision trees

no code implementations NeurIPS 2015 Mohammad Norouzi, Maxwell D. Collins, Matthew Johnson, David J. Fleet, Pushmeet Kohli

In this paper, we present an algorithm for optimizing the split functions at all levels of the tree jointly with the leaf parameters, based on a global objective.

Structured Prediction

Analyzing Hogwild Parallel Gaussian Gibbs Sampling

no code implementations NeurIPS 2013 Matthew Johnson, James Saunderson, Alan Willsky

Sampling inference methods are computationally difficult to scale for many models in part because global dependencies can reduce opportunities for parallel computation.

Cannot find the paper you are looking for? You can Submit a new open access paper.