数字人论文:Audio-Driven Facial Animation by Joint End-to-End Learning of Pose and Emotion

老规矩. 直接第三章

3. 端到端网络结构

给一个audio 短窗口, 也就是片段. 我们预测窗口中间时刻的面部表情.

我们把表情看做一个全端点的向量 (后面我们会看这是什么的一种刻画面部)

一旦我们网络训完, 我们回各个时间点同时生成, 并行. 即使不需要过去的帧画面, 依然生成很稳定的画面. (指的是画面不会跳帧严重, 画面连贯).

本栏目推荐文章
• 《RAPL: A Relation-Aware Prototype Learning Approach for Few-Shot Document-Level Relation Extraction》阅读笔记
• 【五期李伟平】CCF-A（AAAI'21）Game of Gradients: Mitigating Irrelevant Clients in Federated Learning
• Learning Dynamic Query Combinations for Transformer-based Object** Detection and Segmentation论文阅读笔记
• 【略读论文|大模型相关】Zero-Shot Relational Learning on Temporal Knowledge Graphs with Large Language Models
• 《An End-to-end Model for Entity-level Relation Extraction using Multi-instance Learning》阅读笔记
• CF940F Machine Learning题解
• CF940FMachine Learning题解
• 《Ensemble deep learning: A review》阅读笔记
• 二十、属性动画（animation）
• 机器学习Machine Learning

Audio-Driven End-to-End Animation End Learningaudio-driven end-to-end animation end predictron end-to-end end learning end-to-end transformers end-to-end end detection line end-to-end end detection extraction end-to-end generation language augmentation peripheral end-to-end end end-to-end end rfn-nest residual multi-instance entity-level end-to-end extraction high-fidelity parametric animation learning