Taming Consistency Distillation for Accelerated Human Image Animation

• URL: http://arxiv.org/abs/2504.11143v1
• Date: Tue, 15 Apr 2025 12:44:53 GMT
• Title: Taming Consistency Distillation for Accelerated Human Image Animation
• Authors: Xiang Wang, Shiwei Zhang, Hangjie Yuan, Yujie Wei, Yingya Zhang, Changxin Gao, Yuehuan Wang, Nong Sang,
• Abstract summary: DanceLCM achieves results comparable to state-of-the-art video diffusion models with a mere 2-4 inference steps.<n>The code and models will be made publicly available.
• Score: 47.63111489003292
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in human image animation have been propelled by video diffusion models, yet their reliance on numerous iterative denoising steps results in high inference costs and slow speeds. An intuitive solution involves adopting consistency models, which serve as an effective acceleration paradigm through consistency distillation. However, simply employing this strategy in human image animation often leads to quality decline, including visual blurring, motion degradation, and facial distortion, particularly in dynamic regions. In this paper, we propose the DanceLCM approach complemented by several enhancements to improve visual quality and motion continuity at low-step regime: (1) segmented consistency distillation with an auxiliary light-weight head to incorporate supervision from real video latents, mitigating cumulative errors resulting from single full-trajectory generation; (2) a motion-focused loss to centre on motion regions, and explicit injection of facial fidelity features to improve face authenticity. Extensive qualitative and quantitative experiments demonstrate that DanceLCM achieves results comparable to state-of-the-art video diffusion models with a mere 2-4 inference steps, significantly reducing the inference burden without compromising video quality. The code and models will be made publicly available.

Related papers

• REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning [95.07708090428814]
  We present REWIND, a one-step diffusion model for real-time, high-fidelity human motion estimation from egocentric image inputs.<n>We introduce cascaded body-hand denoising diffusion, which effectively models the correlation between egocentric body and hand motions.<n>We also propose a novel identity conditioning method based on a small set of pose exemplars of the target identity, which further enhances motion estimation quality.
  arXiv  Detail & Related papers  (2025-04-07T11:44:11Z)
• One-Step Diffusion Model for Image Motion-Deblurring [85.76149042561507]
  We propose a one-step diffusion model for deblurring (OSDD), a novel framework that reduces the denoising process to a single step.<n>To tackle fidelity loss in diffusion models, we introduce an enhanced variational autoencoder (eVAE), which improves structural restoration.<n>Our method achieves strong performance on both full and no-reference metrics.
  arXiv  Detail & Related papers  (2025-03-09T09:39:57Z)
• Accelerating Video Diffusion Models via Distribution Matching [26.475459912686986]
  This work introduces a novel framework for diffusion distillation and distribution matching. Our approach focuses on distilling pre-trained diffusion models into a more efficient few-step generator. By leveraging a combination of video GAN loss and a novel 2D score distribution matching loss, we demonstrate the potential to generate high-quality video frames.
  arXiv  Detail & Related papers  (2024-12-08T11:36:32Z)
• High Quality Human Image Animation using Regional Supervision and Motion Blur Condition [97.97432499053966]
  We 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.
  arXiv  Detail & Related papers  (2024-09-29T06:46:31Z)
• COIN: Control-Inpainting Diffusion Prior for Human and Camera Motion Estimation [98.05046790227561]
  COIN is a control-inpainting motion diffusion prior that enables fine-grained control to disentangle human and camera motions. COIN outperforms the state-of-the-art methods in terms of global human motion estimation and camera motion estimation.
  arXiv  Detail & Related papers  (2024-08-29T10:36:29Z)
• Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation [134.22372190926362]
  Image diffusion distillation achieves high-fidelity generation with very few sampling steps. Applying these techniques directly to video diffusion often results in unsatisfactory frame quality due to limited visual quality in public video datasets. Our study aims to improve video diffusion distillation while improving frame appearance using abundant high-quality image data.
  arXiv  Detail & Related papers  (2024-06-11T02:09:46Z)
• MotionMix: Weakly-Supervised Diffusion for Controllable Motion Generation [19.999239668765885]
  MotionMix is a weakly-supervised diffusion model that leverages both noisy and unannotated motion sequences. Our framework consistently achieves state-of-the-art performances on text-to-motion, action-to-motion, and music-to-dance tasks.
  arXiv  Detail & Related papers  (2024-01-20T04:58:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.