用手机照片零样本生成高保真3D虚拟人像，保持身份一致性。
Capture, Canonicalize, Splat: Zero-Shot 3D Gaussian Avatars from Unstructured Phone Images
- 通过生成式标准化模块统一多视角无序照片，构建一致表征
- 基于真实人物穹顶采集数据训练，还原皮肤皱纹等高频细节
- 适合想快速生成逼真虚拟形象的创作者和开发者
我们提出一种新型零样本流程，仅需少量无序手机照片即可生成高度逼真、身份一致的3D虚拟人像。现有方法存在单视图几何不一致与幻觉问题，影响身份保留；而基于合成数据训练的模型难以捕捉皮肤皱纹、细发等高频细节，限制真实感。本文方法引入两项关键创新：(1) 生成式标准化模块，将多视角无序图像处理为标准一致的表征；(2) 基于新构建的大规模高质量高斯点云虚拟人数据集（源自真实人物穹顶采集）训练的Transformer模型。该“捕获、标准化、点云化”流程可生成静态半身虚拟人像，在真实感和身份保留方面表现优异。
原文摘要 · Abstract (English)
We present a novel, zero-shot pipeline for creating hyperrealistic, identity-preserving 3D avatars from a few unstructured phone images. Existing methods face several challenges: single-view approaches suffer from geometric inconsistencies and hallucinations, degrading identity preservation, while models trained on synthetic data fail to capture high-frequency details like skin wrinkles and fine hair, limiting realism. Our method introduces two key contributions: (1) a generative canonicalization module that processes multiple unstructured views into a standardized, consistent representation, and (2) a transformer-based model trained on a new, large-scale dataset of high-fidelity Gaussian splatting avatars derived from dome captures of real people. This "Capture, Canonicalize, Splat" pipeline produces static quarter-body avatars with compelling realism and robust identity preservation from unstructured photos.
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。