arXiv:2507.15979cs.GRcs.AI2025-07中稿 · 3DV 2026被引 6

单图生成可动画3D人像,实时渲染且细节丰富

Dream, Lift, Animate: From Single Images to Animatable Gaussian Avatars

  • 用视频扩散模型生成多视角图像,再转为3D高斯点云
  • 通过姿势感知的UV空间映射,实现高质量动画驱动
  • 适合数字人创作、游戏建模,无需后期处理

我们提出Dream, Lift, Animate(DLA)框架,仅需单张图像即可重建可动画的3D人体形象。首先利用视频扩散模型生成合理的多视角图像,捕捉丰富的几何与外观细节;随后将这些视角图像提升为无结构3D高斯点云。为支持动画,设计基于Transformer的编码器,建模全局空间关系,并将高斯点云投影至参数化人体模型的UV空间中,得到结构化潜在表示。该表示解码为UV空间高斯点云,可通过身体驱动形变进行动画,并按姿态和视角渲染。通过将高斯点锚定在UV流形上,方法在动画过程中保持一致性并保留精细视觉特征。DLA支持实时渲染与直观编辑,无需后处理,在ActorsHQ与4D-Dress数据集上均优于现有最佳方法,兼顾感知质量与光度准确性。

原文摘要 · Abstract (English)

We introduce Dream, Lift, Animate (DLA), a novel framework that reconstructs animatable 3D human avatars from a single image. This is achieved by leveraging multi-view generation, 3D Gaussian lifting, and pose-aware UV-space mapping of 3D Gaussians. Given an image, we first dream plausible multi-views using a video diffusion model, capturing rich geometric and appearance details. These views are then lifted into unstructured 3D Gaussians. To enable animation, we propose a transformer-based encoder that models global spatial relationships and projects these Gaussians into a structured latent representation aligned with the UV space of a parametric body model. This latent code is decoded into UV-space Gaussians that can be animated via body-driven deformation and rendered conditioned on pose and viewpoint. By anchoring Gaussians to the UV manifold, our method ensures consistency during animation while preserving fine visual details. DLA enables real-time rendering and intuitive editing without requiring post-processing. Our method outperforms state-of-the-art approaches on the ActorsHQ and 4D-Dress datasets in both perceptual quality and photometric accuracy. By combining the generative strengths of video diffusion models with a pose-aware UV-space Gaussian mapping, DLA bridges the gap between unstructured 3D representations and high-fidelity, animation-ready avatars.

3D生成可动画高斯点云单图建模

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。