最強換臉算法：Few-Shot Adversarial Learning of Realistic Neural Talking Head Models論文解讀
今天爲大家帶來一篇arXiv新上論文，來自三星AI，用於換臉，沒錯，而且不像deepfake那樣要對被換的臉和要換誰的臉，這兩個人的臉的大量數據信息。僅僅憑藉一張A的臉，就能把視頻中B的臉換成A的臉。如果給定A的臉的圖像增多，效果也會越好。論文引起了廣泛關注，作者也提供了demo視頻，在油管上，大家也可以去搜索看看。這篇論文估計是要投ICCV的，目前在arXiv上是第一版，意思就是有些內容有小錯誤
相關文章
- 1. Stack GAN:Text to Photo-realistic Image Synthesiswith Stacked Generative Adversarial Networks 論文解讀
- 2. [論文解讀]Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
- 3. 論文解讀《Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network》SRGAN
- 4. An Attentive Survey of Attention Models 論文閱讀
- 5. 論文筆記《Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning》
- 6. 論文閱讀Domain Adaptation of DPM models
- 7. StackGAN++: Realistic Image Synthesiswith Stacked Generative Adversarial Networks 論文解讀
- 8. 論文閱讀筆記《Meta-Learning of Neural Architectures for Few-Shot Learning》
- 9. 論文閱讀之《Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network》
- 10. 論文閱讀Recursive Deep Models
- 更多相關文章...
- • C# 文本文件的讀寫 - C#教程
- • *.hbm.xml映射文件詳解 - Hibernate教程
- • JDK13 GA發佈：5大特性解讀
- • 算法總結-深度優先算法
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
最新文章
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. Stack GAN:Text to Photo-realistic Image Synthesiswith Stacked Generative Adversarial Networks 論文解讀
- 2. [論文解讀]Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
- 3. 論文解讀《Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network》SRGAN
- 4. An Attentive Survey of Attention Models 論文閱讀
- 5. 論文筆記《Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning》
- 6. 論文閱讀Domain Adaptation of DPM models
- 7. StackGAN++: Realistic Image Synthesiswith Stacked Generative Adversarial Networks 論文解讀
- 8. 論文閱讀筆記《Meta-Learning of Neural Architectures for Few-Shot Learning》
- 9. 論文閱讀之《Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network》
- 10. 論文閱讀Recursive Deep Models