改變頭像：使用快速風格適應對動態3D頭像進行風格化

摘要

本文提出了一種方法，可以快速將動態3D頭像適應於任意文本描述的新風格。在現有的頭像風格化方法中，直接優化方法可以為任意風格產生出色的結果，但速度過慢且需要為每個新輸入重新進行優化過程。使用在大量風格圖像數據集上訓練的前饋網絡的快速近似方法可以快速為新輸入生成結果，但往往無法很好地泛化到新風格並在質量上表現不佳。因此，我們研究了一種新方法，AlteredAvatar，它結合了這兩種方法，並使用元學習框架。在內部迴圈中，模型學習優化以很好地匹配單個目標風格；而在外部迴圈中，模型學習高效地在許多風格之間進行風格化。訓練後，AlteredAvatar 學習了一種初始化方法，可以在少量更新步驟內快速適應新風格，這些風格可以使用文本、參考圖像或二者的組合來指定。我們展示了 AlteredAvatar 可以在速度、靈活性和質量之間取得良好平衡，同時在廣泛的新視角和面部表情中保持一致性。

English

This paper presents a method that can quickly adapt dynamic 3D avatars to arbitrary text descriptions of novel styles. Among existing approaches for avatar stylization, direct optimization methods can produce excellent results for arbitrary styles but they are unpleasantly slow. Furthermore, they require redoing the optimization process from scratch for every new input. Fast approximation methods using feed-forward networks trained on a large dataset of style images can generate results for new inputs quickly, but tend not to generalize well to novel styles and fall short in quality. We therefore investigate a new approach, AlteredAvatar, that combines those two approaches using the meta-learning framework. In the inner loop, the model learns to optimize to match a single target style well; while in the outer loop, the model learns to stylize efficiently across many styles. After training, AlteredAvatar learns an initialization that can quickly adapt within a small number of update steps to a novel style, which can be given using texts, a reference image, or a combination of both. We show that AlteredAvatar can achieve a good balance between speed, flexibility and quality, while maintaining consistency across a wide range of novel views and facial expressions.

改變頭像：使用快速風格適應對動態3D頭像進行風格化

AlteredAvatar: Stylizing Dynamic 3D Avatars with Fast Style Adaptation

摘要

Support