CVAIJul 20, 2025

StableAnimator++: Overcoming Pose Misalignment and Face Distortion for Human Image Animation

arXiv:2507.15064v111 citationsh-index: 57
Originality Incremental advance
AI Analysis

This addresses identity preservation in human image animation for applications like video editing and virtual avatars, representing an incremental improvement over existing methods.

The paper tackles the problem of identity inconsistency in human image animation when reference images and driving videos differ in body size or position, introducing StableAnimator++ which achieves high-quality video generation with improved identity preservation as demonstrated in benchmark experiments.

Current diffusion models for human image animation often struggle to maintain identity (ID) consistency, especially when the reference image and driving video differ significantly in body size or position. We introduce StableAnimator++, the first ID-preserving video diffusion framework with learnable pose alignment, capable of generating high-quality videos conditioned on a reference image and a pose sequence without any post-processing. Building upon a video diffusion model, StableAnimator++ contains carefully designed modules for both training and inference, striving for identity consistency. In particular, StableAnimator++ first uses learnable layers to predict the similarity transformation matrices between the reference image and the driven poses via injecting guidance from Singular Value Decomposition (SVD). These matrices align the driven poses with the reference image, mitigating misalignment to a great extent. StableAnimator++ then computes image and face embeddings using off-the-shelf encoders, refining the face embeddings via a global content-aware Face Encoder. To further maintain ID, we introduce a distribution-aware ID Adapter that counteracts interference caused by temporal layers while preserving ID via distribution alignment. During the inference stage, we propose a novel Hamilton-Jacobi-Bellman (HJB) based face optimization integrated into the denoising process, guiding the diffusion trajectory for enhanced facial fidelity. Experiments on benchmarks show the effectiveness of StableAnimator++ both qualitatively and quantitatively.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes