自回归外观预测用于3D高斯姿态 avatars
Autoregressive Appearance Prediction for 3D Gaussian Avatars
AI总结：
本文提出一种基于3D高斯点划法的avatar模型，通过自回归方法预测外观潜变量，提高渲染稳定性和细节重建质量。
摘要：
一个逼真且沉浸的人类avatar体验需要捕捉精细的个性化细节，如衣物和头发动态、微妙的面部表情和特征运动模式。实现这一目标需要大规模、高质量的数据集，这通常在非常相似的姿势对应不同外观时引入歧义和虚假相关性。在训练过程中拟合这些细节的模型可能会过拟合，导致对新姿势产生不稳定和突兀的外观变化。我们提出了一种具有空间MLP主干的3D高斯点划法avatar模型，该模型同时受姿态和外观潜变量的条件影响。潜变量通过编码器在训练过程中学习，产生一个紧凑的表示，提高重建质量并帮助消除姿态驱动的渲染歧义。在驾驶过程中，我们的预测器自回归地推断潜变量，产生时间上平滑的外观演变和改进的稳定性。总体而言，我们的方法提供了一条稳健且实用的高保真、稳定avatar驾驶路径。
英文摘要：
A photorealistic and immersive human avatar experience demands capturing fine, person-specific details such as cloth and hair dynamics, subtle facial expressions, and characteristic motion patterns. Achieving this requires large, high-quality datasets, which often introduce ambiguities and spurious correlations when very similar poses correspond to different appearances. Models that fit these details during training can overfit and produce unstable, abrupt appearance changes for novel poses. We propose a 3D Gaussian Splatting avatar model with a spatial MLP backbone that is conditioned on both pose and an appearance latent. The latent is learned during training by an encoder, yielding a compact representation that improves reconstruction quality and helps disambiguate pose-driven renderings. At driving time, our predictor autoregressively infers the latent, producing temporally smooth appearance evolution and improved stability. Overall, our method delivers a robust and practical path to high-fidelity, stable avatar driving.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
