Generative Motion Infilling from Imprecisely Timed Keyframes

Abstract Keyframes are a standard representation for kinematic motion specification. Recent learned motion‐inbetweening methods use keyframes as a way to control generative motion models, and are trained to generate life‐like motion that matches the exact poses and timings of input keyframes. However, the quality of generated motion may degrade if the timing of these constraints is not perfectly consistent with the desired motion. Unfortunately, correctly specifying keyframe timings is a tedious and challenging task in practice. Our goal is to create a system that synthesizes high‐quality motion from keyframes, even if keyframes are imprecisely timed. We present a method that allows constraints to be retimed as part of the generation process. Specifically, we introduce a novel model architecture that explicitly outputs a time‐warping function to correct mistimed keyframes and spatial residuals that add pose details. We demonstrate how our method can automatically turn approximately timed keyframe constraints into diverse, realistic motions with plausible timing and detailed submovements.

Authors

Institutions

Publication Details

Journal
Computer Graphics Forum
Published
2025-04-18
DOI
https://doi.org/10.1111/cgf.70060
Citations
2
Primary Topic
Human Motion and Animation
Type
article
Field-Weighted Citation Impact
2.43
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Generative Motion Infilling from Imprecisely Timed Keyframes

Kayvon Fatahalian, C. Karen Liu, Purvi Goel, Haotian Zhang
2 citations
Computer Graphics Forum
Human Motion and Animation
2.43
article

Generative Motion Infilling from Imprecisely Timed Keyframes

Kayvon Fatahalian, C. Karen Liu, Purvi Goel, Haotian Zhang
article en
2 citations

Abstract

Abstract Keyframes are a standard representation for kinematic motion specification. Recent learned motion‐inbetweening methods use keyframes as a way to control generative motion models, and are trained to generate life‐like motion that matches the exact poses and timings of input keyframes. However, the quality of generated motion may degrade if the timing of these constraints is not perfectly consistent with the desired motion. Unfortunately, correctly specifying keyframe timings is a tedious and challenging task in practice. Our goal is to create a system that synthesizes high‐quality motion from keyframes, even if keyframes are imprecisely timed. We present a method that allows constraints to be retimed as part of the generation process. Specifically, we introduce a novel model architecture that explicitly outputs a time‐warping function to correct mistimed keyframes and spatial residuals that add pose details. We demonstrate how our method can automatically turn approximately timed keyframe constraints into diverse, realistic motions with plausible timing and detailed submovements.

Computer Graphics ForumVol. 44(2)
Stanford University (US)
Openalex Percentile: Top 12%
Human Motion and Animation
2.43
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Generative Motion Infilling from Imprecisely Timed Keyframes — Kayvon Fatahalian, C. Karen Liu, et al. · Computer Graphics Forum (2025) | TGRS Research Map | TGRS