Camera Tracking in Visual Effects - An Industry Perspective of Structure From Motion

Alastair Barber; Darren Cosker; Oliver James; Ted Waine; Radhika Patel

doi:10.1145/2947688.2947697

Camera Tracking in Visual Effects - An Industry Perspective of Structure From Motion

Alastair Barber, Darren Cosker, Oliver James, Ted Waine, Radhika Patel

Double Negative Ltd

Research output: Contribution to conference › Paper › peer-review

9 Citations (SciVal)

613 Downloads (Pure)

Abstract

The ‘Matchmove’, or camera-tracking process is a crucial task and
one of the first to be performed in the visual effects pipeline. An
accurate solve for camera movement is imperative and will have
an impact on almost every other part of the pipeline downstream.
In this work we present a comprehensive analysis of the process
at a major visual effects studio, drawing on a large dataset of real
shots. We also present guidelines and rules-of-thumb for camera
tracking scheduling which are, in what we believe to be an industry
first, backed by statistical data drawn from our dataset. We also
make available data from our pipeline which shows the amount of
time spent on camera tracking and the types of shot that are most
common in our work. We hope this will be of interest to the wider
computer vision research community and will assist in directing
future research.

Original language	English
Number of pages	10
DOIs	https://doi.org/10.1145/2947688.2947697
Publication status	Published - Jul 2016
Event	Digital Production Symposium 2016 - Anaheim, CA., USA United States Duration: 23 Jul 2016 → 23 Jul 2016 http://dp2016.digiproconf.org/

Conference

Conference	Digital Production Symposium 2016
Abbreviated title	DigiPro '16
Country/Territory	USA United States
City	Anaheim, CA.
Period	23/07/16 → 23/07/16
Internet address	http://dp2016.digiproconf.org/

Keywords

Matchmove, Camera Tracking, Structure from Mo- tion, VFX, Motion Pictures

Access to Document

10.1145/2947688.2947697

Camera Ready Full Text
© ACM, 2016. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in Proceedings of the 2016 Symposium on Digital Production, http://doi.acm.org/10.1145/2947688.2947697
Final published version, 1.54 MBLicence: Unspecified

Cite this

@conference{993614bcd81a45b8b12c9611d9d2c622,

title = "Camera Tracking in Visual Effects - An Industry Perspective of Structure From Motion",

abstract = "The {\textquoteleft}Matchmove{\textquoteright}, or camera-tracking process is a crucial task andone of the first to be performed in the visual effects pipeline. Anaccurate solve for camera movement is imperative and will havean impact on almost every other part of the pipeline downstream.In this work we present a comprehensive analysis of the processat a major visual effects studio, drawing on a large dataset of realshots. We also present guidelines and rules-of-thumb for cameratracking scheduling which are, in what we believe to be an industryfirst, backed by statistical data drawn from our dataset. We alsomake available data from our pipeline which shows the amount oftime spent on camera tracking and the types of shot that are mostcommon in our work. We hope this will be of interest to the widercomputer vision research community and will assist in directingfuture research.",

keywords = "Matchmove, Camera Tracking, Structure from Mo- tion, VFX, Motion Pictures",

author = "Alastair Barber and Darren Cosker and Oliver James and Ted Waine and Radhika Patel",

year = "2016",

month = jul,

doi = "10.1145/2947688.2947697",

language = "English",

note = "Digital Production Symposium 2016, DigiPro '16 ; Conference date: 23-07-2016 Through 23-07-2016",

url = "http://dp2016.digiproconf.org/",

}

TY - CONF

T1 - Camera Tracking in Visual Effects - An Industry Perspective of Structure From Motion

AU - Barber, Alastair

AU - Cosker, Darren

AU - James, Oliver

AU - Waine, Ted

AU - Patel, Radhika

PY - 2016/7

Y1 - 2016/7

N2 - The ‘Matchmove’, or camera-tracking process is a crucial task andone of the first to be performed in the visual effects pipeline. Anaccurate solve for camera movement is imperative and will havean impact on almost every other part of the pipeline downstream.In this work we present a comprehensive analysis of the processat a major visual effects studio, drawing on a large dataset of realshots. We also present guidelines and rules-of-thumb for cameratracking scheduling which are, in what we believe to be an industryfirst, backed by statistical data drawn from our dataset. We alsomake available data from our pipeline which shows the amount oftime spent on camera tracking and the types of shot that are mostcommon in our work. We hope this will be of interest to the widercomputer vision research community and will assist in directingfuture research.

AB - The ‘Matchmove’, or camera-tracking process is a crucial task andone of the first to be performed in the visual effects pipeline. Anaccurate solve for camera movement is imperative and will havean impact on almost every other part of the pipeline downstream.In this work we present a comprehensive analysis of the processat a major visual effects studio, drawing on a large dataset of realshots. We also present guidelines and rules-of-thumb for cameratracking scheduling which are, in what we believe to be an industryfirst, backed by statistical data drawn from our dataset. We alsomake available data from our pipeline which shows the amount oftime spent on camera tracking and the types of shot that are mostcommon in our work. We hope this will be of interest to the widercomputer vision research community and will assist in directingfuture research.

KW - Matchmove, Camera Tracking, Structure from Mo- tion, VFX, Motion Pictures

UR - https://doi.org/10.1145/2947688.2947697

U2 - 10.1145/2947688.2947697

DO - 10.1145/2947688.2947697

M3 - Paper

T2 - Digital Production Symposium 2016

Y2 - 23 July 2016 through 23 July 2016

ER -

Camera Tracking in Visual Effects - An Industry Perspective of Structure From Motion

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA)

EPSRC Centre for Doctoral Training in Digital Entertainment

Darren Cosker

Cite this

Camera Tracking in Visual Effects - An Industry Perspective of Structure From Motion

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Projects

Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA)

EPSRC Centre for Doctoral Training in Digital Entertainment

Profiles

Darren Cosker

Cite this