High Quality Human Image Animation using Regional Supervision and Motion Blur Condition
This work addresses the need for more realistic human animation in video generation, though it is incremental by building on existing video diffusion models.
The paper tackles the problem of low-quality human image animation by introducing regional supervision for face and hands and explicit motion blur modeling, resulting in a 21.0% improvement in reconstruction precision and 57.4% in perceptual quality over the strongest baseline.
Recent advances in video diffusion models have enabled realistic and controllable human image animation with temporal coherence. Although generating reasonable results, existing methods often overlook the need for regional supervision in crucial areas such as the face and hands, and neglect the explicit modeling for motion blur, leading to unrealistic low-quality synthesis. To address these limitations, we first leverage regional supervision for detailed regions to enhance face and hand faithfulness. Second, we model the motion blur explicitly to further improve the appearance quality. Third, we explore novel training strategies for high-resolution human animation to improve the overall fidelity. Experimental results demonstrate that our proposed method outperforms state-of-the-art approaches, achieving significant improvements upon the strongest baseline by more than 21.0% and 57.4% in terms of reconstruction precision (L1) and perceptual quality (FVD) on HumanDance dataset. Code and model will be made available.