One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer

TL;DR

This paper introduces One-to-All Animation, a novel framework that enables high-fidelity, alignment-free character animation and image pose transfer, effectively handling arbitrary reference layouts and partial visibility.

Contribution

It reformulates pose transfer as a self-supervised outpainting task and introduces a hybrid reference fusion attention mechanism for improved animation quality.

Findings

Outperforms existing methods in diverse pose transfer tasks.

Effectively handles spatial misalignment and partial visibility.

Achieves high-fidelity animation with identity-robust pose control.

Abstract

Recent advances in diffusion models have greatly improved pose-driven character animation. However, existing methods are limited to spatially aligned reference-pose pairs with matched skeletal structures. Handling reference-pose misalignment remains unsolved. To address this, we present One-to-All Animation, a unified framework for high-fidelity character animation and image pose transfer for references with arbitrary layouts. First, to handle spatially misaligned reference, we reformulate training as a self-supervised outpainting task that transforms diverse-layout reference into a unified occluded-input format. Second, to process partially visible reference, we design a reference extractor for comprehensive identity feature extraction. Further, we integrate hybrid reference fusion attention to handle varying resolutions and dynamic sequence lengths. Finally, from the perspective of generation quality, we introduce identity-robust pose control that decouples appearance from skeletal structure to mitigate pose overfitting, and a token replace strategy for coherent long-video generation. Extensive experiments show that our method outperforms existing approaches. The code and model are available at https://github.com/ssj9596/One-to-All-Animation.