SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation

2025-11-24

AI Summary

Human image animation faces the challenge of simultaneously preserving subject identity from the source frame and achieving precise motion control. Existing reference-to-video (R2V) methods often neglect spatiotemporal misalignment, leading to identity drift and visual artifacts. This paper proposes a novel diffusion-driven image-to-video animation framework. First, it achieves strong, robust identity preservation from the initial frame. Second, it introduces a conditional coordination mechanism and a collaborative pose modulation module to explicitly decouple appearance and motion modeling, thereby balancing controllability and fidelity. Third, it employs a staged decoupled training strategy coupled with adaptive pose representation learning. Evaluated on multiple benchmarks, our method achieves state-of-the-art performance: it significantly suppresses identity drift and artifacts, improves temporal consistency, and reduces training resource consumption by over 30%.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Machine Learning: Multimodal Learning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Preserving first-frame identity while ensuring precise motion control is a fundamental challenge in human image animation. The Image-to-Motion Binding process of the dominant Reference-to-Video (R2V) paradigm overlooks critical spatio-temporal misalignments common in real-world applications, leading to failures such as identity drift and visual artifacts. We introduce SteadyDancer, an Image-to-Video (I2V) paradigm-based framework that achieves harmonized and coherent animation and is the first to ensure first-frame preservation robustly. Firstly, we propose a Condition-Reconciliation Mechanism to harmonize the two conflicting conditions, enabling precise control without sacrificing fidelity. Secondly, we design Synergistic Pose Modulation Modules to generate an adaptive and coherent pose representation that is highly compatible with the reference image. Finally, we employ a Staged Decoupled-Objective Training Pipeline that hierarchically optimizes the model for motion fidelity, visual quality, and temporal coherence. Experiments demonstrate that SteadyDancer achieves state-of-the-art performance in both appearance fidelity and motion control, while requiring significantly fewer training resources than comparable methods.

Problem

• Preserving first-frame identity during human animation
• Addressing spatio-temporal misalignments in motion control
• Preventing identity drift and visual artifacts

Innovation

• Condition-Reconciliation Mechanism harmonizes conflicting conditions
• Synergistic Pose Modulation generates adaptive pose representation
• Staged Decoupled-Objective Training hierarchically optimizes model objectives