MultiAnimate: A Unified Framework for Controllable Multi-Character Animation

2026-07-14

AI Summary

Existing methods struggle to generate multi-character cooperative animations that maintain consistent identities and plausible spatial relationships. To address this challenge, this work proposes a unified framework that, for the first time, enables identity-preserving animation from multiple reference images by extracting distinct identity features for each character. The framework employs an identity-aware pose encoder together with an attention-based multi-sequence processing mechanism to disentangle and synchronize pose sequences across multiple characters. Additionally, it incorporates an interaction-guided module and optional character masks to effectively model spatial relationships in complex interactive scenarios. Experimental results demonstrate that the proposed method significantly outperforms existing approaches in multi-character animation generation, particularly excelling in scenes involving intricate motions and rich character interactions.

Abstract

Recent advances in generative models and technological innovations have significantly addressed the fundamental challenges of character image animation. However, existing approaches predominantly focus on character animation from a single reference image, substantially limiting their applicability in scenarios such as multiple character interaction animation. To fill this gap, this paper introduces MultiAnimate, a comprehensive framework that enables concurrent animation of multiple characters within a shared environment while preserving both identity consistency and spatial relationships. The framework achieves these objectives through multiple well-designed mechanisms. First, we incorporate an identity-specific reference net that enables appearance extraction from multiple reference images, distinguishing MultiAnimate from existing approaches constrained to single reference inputs. Second, we implement an identity-aware pose encoder to address the character-pose binding challenge, wherein an attention mechanism enables the network to accurately differentiate and process multiple pose sequences during generation. Third, we introduce an interaction guider module that enhances the framework's capability to handle complex inter-character interactions by leveraging character-specific mask information, serving as an optional component that refines the pose sequences. Extensive experiments and ablation analyses demonstrate our framework's superiority in multiple character animation, particularly in scenarios involving complex motion sequences.

Problem

• multi-character animation
• identity consistency
• spatial relationships
• character interaction
• reference-based animation

Innovation

• multi-character animation
• identity consistency
• pose encoding
• reference-based generation
• interaction modeling