Motion Puzzle: Arbitrary Motion Style Transfer by Body Part

Abstract

This paper presents Motion Puzzle, a novel motion style transfer network that advances the state-of-the-art in several important respects. The Motion Puzzle is the first that can control the motion style of individual body parts, allowing for local style editing and significantly increasing the range of stylized motions. Designed to keep the human's kinematic structure, our framework extracts style features from multiple style motions for different body parts and transfers them locally to the target body parts. Another major advantage is that it can transfer both global and local traits of motion style by integrating the adaptive instance normalization and attention modules while keeping the skeleton topology. Thus, it can capture styles exhibited by dynamic movements, such as flapping and staggering, significantly better than previous work. In addition, our framework allows for arbitrary motion style transfer without datasets with style labeling or motion pairing, making many publicly available motion datasets available for training. Our framework can be easily integrated with motion generation frameworks to create many applications, such as real-time motion transfer. We demonstrate the advantages of our framework with a number of examples and comparisons with previous work.

16 pages

References in corpus (3)

• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Skeleton-Aware Networks for Deep Motion Retargeting
• Unpaired Motion Style Transfer from Video to Animation

Cited by in corpus (14)

• Composite Motion Learning with Task Control
• RSMT: Real-time Stylized Motion Transition for Characters
• Pose-aware Attention Network for Flexible Motion Retargeting by Body Part
• LGTM: Local-to-Global Text-Driven Human Motion Diffusion Model
• MOCHA: Real-Time Motion Characterization via Context Matching
• MOVIN: Real-time Motion Capture using a Single LiDAR
• Decoupling Contact for Fine-Grained Motion Style Transfer
• An Implicit Physical Face Model Driven by Expression and Style
• A Two-part Transformer Network for Controllable Motion Synthesis
• AStF: Motion Style Transfer via Adaptive Statistics Fusor
• Motion Style Slider: Endpoint-Supervised Continuous Style Control for Human Motion Diffusion
• D-LORD for Motion Stylization
• STyMo: Fast and Controllable Few-Shot Motion Style Transfer
• ExpertEdit: Learning Skill-Aware Motion Editing from Expert Videos