Skip to main navigation Skip to search Skip to main content

Rethinking motion keyframe extraction: a greedy procedural approach using a neural control rig

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

3D animators traditionally use a "pose to pose"approach, whereas motion capture (MoCap) tools generate a pose for every frame, making the motion challenging to edit. We argue that current keyframe extraction methods are inadequate for human editing. To address this, we propose a novel approach that bridges the gap between MoCap animations and traditional 3D artist tools. Our contributions include learning a neural control rig as a differentiable proxy for more accurate key pose interpolation and formulating the task as an optimization problem, solved efficiently with a greedy dynamic programming algorithm.

Original languageEnglish
Title of host publicationProceedings - SIGGRAPH Asia 2024 Posters, SA 2024
EditorsStephen N. Spencer
PublisherAssociation for Computing Machinery, Inc
ISBN (Electronic)9798400711381
DOIs
Publication statusPublished - 3 Dec 2024
Event2024 SIGGRAPH Asia 2024 Posters, SA 2024 - Tokyo, Japan
Duration: 3 Dec 20246 Dec 2024

Publication series

NameProceedings - SIGGRAPH Asia 2024 Posters, SA 2024

Conference

Conference2024 SIGGRAPH Asia 2024 Posters, SA 2024
Country/TerritoryJapan
CityTokyo
Period3/12/246/12/24

Fingerprint

Dive into the research topics of 'Rethinking motion keyframe extraction: a greedy procedural approach using a neural control rig'. Together they form a unique fingerprint.

Cite this