MotionCanvas creates realistic character movements from simple instructions
MotionCanvas: Learning Implicit Motion Planning from Composable Kinematic Cues
Multimedia
Summary
Creating realistic animation for characters requires both natural-looking movements and precise control over how the character moves. The authors propose MotionCanvas, a system that lets animators specify simple cues like body part positions, rotations, or timing on a shared canvas, and then generates a complete, smooth motion sequence that matches those cues. This model can combine different types of input cues, including language instructions, to produce coherent full-body movements. The method also works well for editing motions or fixing them when something looks off. Overall, MotionCanvas improves the quality and control of generated character animations.
character animationkinematic cuesmotion planningflow matchingmotion generationcue conditioningimplicit motion modelinglanguage-guided editingmotion repairsequential generation
Authors
Zeyu Ling, Di Kang, Qing Shuai, Yuxin Wen, Jing Li, Zhanke Wang, Heng Li, Changqing Zou, Chunchao Guo, Linchao Bao
Abstract
Professional character animation requires both natural motion and precise, versatile control. For example, it is common for the creators to define the timing of a specified action, to control the motion range of the character's arm swing, and the route the character walks through, like specifying various kinematic motion cues on a ``motion canvas''. This motivates us to propose MotionCanvas, a model that supports \emph{cue-conditioned implicit motion planning} to faithfully and coherently connect all cues, dense or sparse, full or partial, into one full-body motion sequence. Specifically, MotionCanvas represents heterogeneous kinematic cues on a shared motion canvas, where position and rotation values are specified across body joints and time. A shared flow-matching model generates motion conditioned on this canvas, with optional language and input motion; cue imputation keeps the specified canvas values fixed in both training and sampling. To learn coherent completion across different cue sets, we train with a compositional cue sampler that varies when cues are applied, which positions or rotations are specified, and how they are combined. Together, these designs enable a single generator to synthesize globally coherent actions that jointly satisfy compatible heterogeneous cues. We test this planning ability with temporal, root, and body-part cues---alone and in combination---and language-guided editing. We naturally extend this evaluation to sequential generation and motion repair, since both require the same ability to organize coherent motion from kinematic cues. Across these evaluations, MotionCanvas establishes state-of-the-art results in controlled-motion quality, mixed-cue adherence, sequential generation, instruction editing, and motion repair while preserving its text-to-motion capability.