TY - GEN
T1 - Rethinking motion keyframe extraction
T2 - 2024 SIGGRAPH Asia 2024 Posters, SA 2024
AU - Cheynel, Théo
AU - El Khalifi, Omar
AU - Bellot-Gurlet, Baptiste
AU - Rohmer, Damien
AU - Cani, Marie Paule
N1 - Publisher Copyright:
© 2024 Copyright held by the owner/author(s).
PY - 2024/12/3
Y1 - 2024/12/3
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/85215536253
U2 - 10.1145/3681756.3697960
DO - 10.1145/3681756.3697960
M3 - Conference contribution
AN - SCOPUS:85215536253
T3 - Proceedings - SIGGRAPH Asia 2024 Posters, SA 2024
BT - Proceedings - SIGGRAPH Asia 2024 Posters, SA 2024
A2 - Spencer, Stephen N.
PB - Association for Computing Machinery, Inc
Y2 - 3 December 2024 through 6 December 2024
ER -