MacAction: Realistic 3D macaque body animation based on multi-camera markerless motion capture DOI Creative Commons
Lucas Martini, Anna Bognár, Rufin Vogels

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Jan. 30, 2024

Abstract Social interaction is crucial for survival in primates. For the study of social vision monkeys, highly controllable macaque face avatars have recently been developed, while body with realistic motion do not yet exist. Addressing this gap, we developed a pipeline three-dimensional tracking based on synchronized multi-view video recordings, achieving sufficient accuracy life-like full-body animation. By exploiting data-driven pose estimation models, track complete time course individual actions using minimal set hand-labeled keyframes. Our approach tracks single more accurately than existing pipelines behavioral non-human primates, requiring less data and fewer cameras. This efficiency also confirmed state-of-the-art human benchmark dataset. A experiment real monkeys demonstrates that animals perceive generated animations as similar to genuine videos, establishes an uncanny valley effect bodies monkeys.

Language: Английский

MacAction: Realistic 3D macaque body animation based on multi-camera markerless motion capture DOI Creative Commons
Lucas Martini, Anna Bognár, Rufin Vogels

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Jan. 30, 2024

Abstract Social interaction is crucial for survival in primates. For the study of social vision monkeys, highly controllable macaque face avatars have recently been developed, while body with realistic motion do not yet exist. Addressing this gap, we developed a pipeline three-dimensional tracking based on synchronized multi-view video recordings, achieving sufficient accuracy life-like full-body animation. By exploiting data-driven pose estimation models, track complete time course individual actions using minimal set hand-labeled keyframes. Our approach tracks single more accurately than existing pipelines behavioral non-human primates, requiring less data and fewer cameras. This efficiency also confirmed state-of-the-art human benchmark dataset. A experiment real monkeys demonstrates that animals perceive generated animations as similar to genuine videos, establishes an uncanny valley effect bodies monkeys.

Language: Английский

Citations

0