Search Results for author: Andrew Fitzgibbon

Found 29 papers, 6 papers with code

FLAG: Flow-based 3D Avatar Generation from Sparse Observations

no code implementations CVPR 2022 Sadegh Aliakbarian, Pashmina Cameron, Federica Bogo, Andrew Fitzgibbon, Thomas J. Cashman

To represent people in mixed reality applications for collaboration and communication, we need to generate realistic and faithful avatar poses.

Mixed Reality

Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loop

2 code implementations ECCV 2020 Benjamin Biggs, Oliver Boyne, James Charles, Andrew Fitzgibbon, Roberto Cipolla

We introduce an automatic, end-to-end method for recovering the 3D pose and shape of dogs from monocular internet images.

Inverse Graphics GAN: Learning to Generate 3D Shapes from Unstructured 2D Data

no code implementations28 Feb 2020 Sebastian Lunz, Yingzhen Li, Andrew Fitzgibbon, Nate Kushman

In this paper we introduce the first scalable training technique for 3D generative models from 2D data which utilizes an off-the-shelf non-differentiable renderer.

A Benchmark of Selected Algorithmic Differentiation Tools on Some Problems in Computer Vision and Machine Learning

3 code implementations26 Jul 2018 Filip Šrajer, Zuzana Kukelova, Andrew Fitzgibbon

However, it is important for the success of algorithmic differentiation that such `simple' objective functions are handled efficiently, as so many problems in computer vision and machine learning are of this form.

BIG-bench Machine Learning

Hybrid VAE: Improving Deep Generative Models using Partial Observations

no code implementations30 Nov 2017 Sergey Tulyakov, Andrew Fitzgibbon, Sebastian Nowozin

We show that such a combination is beneficial because the unlabeled data acts as a data-driven form of regularization, allowing generative models trained on few labeled samples to reach the performance of fully-supervised generative models trained on much larger datasets.

Better Together: Joint Reasoning for Non-rigid 3D Reconstruction with Specularities and Shading

no code implementations4 Aug 2017 Qi Liu-Yin, Rui Yu, Lourdes Agapito, Andrew Fitzgibbon, Chris Russell

We demonstrate the use of shape-from-shading (SfS) to improve both the quality and the robustness of 3D reconstruction of dynamic objects captured by a single camera.

3D Reconstruction Object Tracking

An Efficient Background Term for 3D Reconstruction and Tracking With Smooth Surface Models

no code implementations CVPR 2017 Mariano Jaimez, Thomas J. Cashman, Andrew Fitzgibbon, Javier Gonzalez-Jimenez, Daniel Cremers

We present a novel strategy to shrink and constrain a 3D model, represented as a smooth spline-like surface, within the visual hull of an object observed from one or multiple views.

3D Reconstruction Object Tracking +1

Revisiting the Variable Projection Method for Separable Nonlinear Least Squares Problems

no code implementations CVPR 2017 Je Hyeong Hong, Christopher Zach, Andrew Fitzgibbon

Variable Projection (VarPro) is a framework to solve optimization problems efficiently by optimally eliminating a subset of the unknowns.

On the Two-View Geometry of Unsynchronized Cameras

2 code implementations CVPR 2017 Cenek Albl, Zuzana Kukelova, Andrew Fitzgibbon, Jan Heller, Matej Smid, Tomas Pajdla

We present new methods for simultaneously estimating camera geometry and time shift from video sequences from multiple unsynchronized cameras.

Fits Like a Glove: Rapid and Reliable Hand Shape Personalization

no code implementations CVPR 2016 David Joseph Tan, Thomas Cashman, Jonathan Taylor, Andrew Fitzgibbon, Daniel Tarlow, Sameh Khamis, Shahram Izadi, Jamie Shotton

We present a fast, practical method for personalizing a hand shape basis to an individual user's detailed hand shape using only a small set of depth images.

Reflection Modeling for Passive Stereo

no code implementations ICCV 2015 Rahul Nair, Andrew Fitzgibbon, Daniel Kondermann, Carsten Rother

Stereo reconstruction in presence of reality faces many challenges that still need to be addressed.

Secrets of Matrix Factorization: Approximations, Numerics, Manifold Optimization and Random Restarts

no code implementations ICCV 2015 Je Hyeong Hong, Andrew Fitzgibbon

Matrix factorization (or low-rank matrix completion) with missing data is a key computation in many computer vision and machine learning tasks, and is also related to a broader class of nonlinear optimization problems such as bundle adjustment.

Low-Rank Matrix Completion

Model-Based Tracking at 300Hz Using Raw Time-of-Flight Observations

no code implementations ICCV 2015 Jan Stuhmer, Sebastian Nowozin, Andrew Fitzgibbon, Richard Szeliski, Travis Perry, Sunil Acharya, Daniel Cremers, Jamie Shotton

In this paper, we show how to perform model-based object tracking which allows to reconstruct the object's depth at an order of magnitude higher frame-rate through simple modifications to an off-the-shelf depth camera.

Object Tracking

Towards Pointless Structure From Motion: 3D Reconstruction and Camera Parameters From General 3D Curves

no code implementations ICCV 2015 Irina Nurutdinova, Andrew Fitzgibbon

Modern structure from motion (SfM) remains dependent on point features to recover camera positions, meaning that reconstruction is severely hampered in low-texture environments, for example scanning a plain coffee cup on an uncluttered table.

3D Reconstruction

Learning an Efficient Model of Hand Shape Variation From Depth Images

no code implementations CVPR 2015 Sameh Khamis, Jonathan Taylor, Jamie Shotton, Cem Keskin, Shahram Izadi, Andrew Fitzgibbon

We represent the observed surface using Loop subdivision of a control mesh that is deformed by our learned parametric shape and pose model.

Multi-Output Learning for Camera Relocalization

no code implementations CVPR 2014 Abner Guzman-Rivera, Pushmeet Kohli, Ben Glocker, Jamie Shotton, Toby Sharp, Andrew Fitzgibbon, Shahram Izadi

We formulate this problem as inversion of the generative rendering procedure, i. e., we want to find the camera pose corresponding to a rendering of the 3D scene model that is most similar with the observed input.

3D Reconstruction Camera Relocalization

SphereFlow: 6 DoF Scene Flow from RGB-D Pairs

no code implementations CVPR 2014 Michael Hornacek, Andrew Fitzgibbon, Carsten Rother

As a consequence of our approach, our output is a dense field of 3D rigid body motions, in contrast to the 3D translations that are the norm in scene flow.

Occlusion Handling

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