用对抗生成技术让3D高斯头像实时可动，兼顾画质与性能。
AGORA: Adversarial Generation Of Real-time Animatable 3D Gaussian Head Avatars
- 基于3D高斯泼溅+对抗训练，生成可动画的逼真头部模型
- 单卡渲染达560帧/秒，手机端也能保持60帧流畅运行
- 支持移动端即时动画，适合虚拟人、VR和远程会议场景
高保真、可动画化的3D人类头像生成仍是计算机图形学与视觉领域的核心挑战，广泛应用于虚拟现实、远程通信和娱乐。现有基于隐式表示（如NeRF）的方法存在渲染慢、动态不一致的问题，而3D高斯泼溅（3DGS）方法通常仅限于静态头像生成，缺乏动态控制能力。本文提出AGORA，一种新颖框架，在生成对抗网络中扩展3DGS，实现可动画化头像生成。该方法结合空间形状条件与双判别器训练策略，分别监督渲染外观与合成几何特征，显著提升表情真实度与可控性。为支持实际部署，我们引入一种简单的推理时方法，提取高斯混合形状并复用于设备端动画。AGORA生成的头像视觉逼真、控制精确，在可动画生成头像方法中达到当前最佳表现。定量结果显示，单卡可实现560帧/秒渲染，移动设备上亦能维持60帧/秒，为高性能数字人应用迈出关键一步。
原文摘要 · Abstract (English)
The generation of high-fidelity, animatable 3D human avatars remains a core challenge in computer graphics and vision, with applications in VR, telepresence, and entertainment. Existing approaches based on implicit representations like NeRFs suffer from slow rendering and dynamic inconsistencies, while 3D Gaussian Splatting (3DGS) methods are typically limited to static head generation, lacking dynamic control. We bridge this gap by introducing AGORA, a novel framework that extends 3DGS within a generative adversarial network to produce animatable avatars. Our formulation combines spatial shape conditioning with a dual-discriminator training strategy that supervises both rendered appearance and synthetic geometry cues, improving expression fidelity and controllability. To enable practical deployment, we further introduce a simple inference-time approach that extracts Gaussian blendshapes and reuses them for animation on-device. AGORA generates avatars that are visually realistic, precisely controllable, and achieves state-of-the-art performance among animatable generative head-avatar methods. Quantitatively, we render at 560 FPS on a single GPU and 60 FPS on mobile phones, marking a significant step toward practical, high-performance digital humans. Project website: https://ramazan793.github.io/AGORA/
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。