Controllable Single-shot Animation Blending with Temporal Conditioning

2025-08-25

AI Summary

Existing single-shot motion generation models lack explicit temporal control for multi-action fusion. This paper introduces the first controllable temporal motion blending framework tailored for few-shot scenarios, enabling seamless and user-controllable mixing of multiple actions within a single skeletal sequence—without requiring predefined kinematic trees or skeleton constraints. Our method comprises: (1) a time-conditioned generative architecture that supports user-specified fusion timing and transition styles; (2) a skeleton-aware normalization mechanism ensuring consistent representation across diverse skeletons and motion styles; and (3) a few-shot motion representation learning strategy. We validate the framework’s generality, efficiency, and high-fidelity synthesis capability across varied skeletal configurations and animation styles. Experimental results demonstrate significant improvements in both controllability—e.g., precise temporal alignment and customizable transitions—and naturalness of blended motions, establishing a new benchmark for few-shot controllable motion synthesis.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Temporal Planning

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs

Abstract

Training a generative model on a single human skeletal motion sequence without being bound to a specific kinematic tree has drawn significant attention from the animation community. Unlike text-to-motion generation, single-shot models allow animators to controllably generate variations of existing motion patterns without requiring additional data or extensive retraining. However, existing single-shot methods do not explicitly offer a controllable framework for blending two or more motions within a single generative pass. In this paper, we present the first single-shot motion blending framework that enables seamless blending by temporally conditioning the generation process. Our method introduces a skeleton-aware normalization mechanism to guide the transition between motions, allowing smooth, data-driven control over when and how motions blend. We perform extensive quantitative and qualitative evaluations across various animation styles and different kinematic skeletons, demonstrating that our approach produces plausible, smooth, and controllable motion blends in a unified and efficient manner.

Problem

• Enabling controllable blending of multiple motions in single generative pass
• Providing seamless transition between motions with temporal conditioning
• Achieving smooth data-driven motion blending across various animation styles

Innovation

• Temporal conditioning for seamless motion blending
• Skeleton-aware normalization for smooth transitions
• Single-shot framework for unified motion generation