[ICCV2019] Unsupervised Robust Disentangling of Latent Characteristics for Image Synthesis
作者：Patrick Esser，Heidelberg University, Germany Distanglement 何谓解耦。举例说明下：一张人像图，普通编码器会将这幅图的所有信息进行编码，包括人的外观，姿势，背景等，但这些特征是耦合的，即在改变编码向量时，你无法单独改变某一特征，而不影响其他特征；而distangle意味着图像中这些不同的特征在编码后，可以单独改变而不相互影响。 本文中把
相关文章
- 1. 论文笔记（1）：CVPR2019-Latent Filter Scaling for Multimodal Unsupervised Image-to-Image Translation
- 2. Unsupervised Disentangling of Appearance and Geometry by Deformable Generator Network
- 3. Unsupervised Person Image Synthesis in Arbitrary Poses 笔记
- 4. Generative Adversarial Text to Image Synthesis
- 5. Uncovering Latent Style Factors for Expressive Speech Synthesis
- 6. SDGAN 《Semantics Disentangling for Text-to-Image Generation》探析
- 7. Unpaired/Partially/Unsupervised Image Captioning
- 8. Y-Autoencoders: disentangling latent representations via sequential-encoding
- 9. image characteristics extraction
- 10. LARGE SCALE GAN TRAINING FOR HIGH FIDELITY NATURAL IMAGE SYNTHESIS
- 更多相关文章...
- • Scala for循环 - Scala教程
- • RSS
元素 - RSS 教程 - • Docker 清理命令
- • 使用Rxjava计算圆周率
相关标签/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。
欢迎关注本站公众号,获取更多信息
相关文章
- 1. 论文笔记（1）：CVPR2019-Latent Filter Scaling for Multimodal Unsupervised Image-to-Image Translation
- 2. Unsupervised Disentangling of Appearance and Geometry by Deformable Generator Network
- 3. Unsupervised Person Image Synthesis in Arbitrary Poses 笔记
- 4. Generative Adversarial Text to Image Synthesis
- 5. Uncovering Latent Style Factors for Expressive Speech Synthesis
- 6. SDGAN 《Semantics Disentangling for Text-to-Image Generation》探析
- 7. Unpaired/Partially/Unsupervised Image Captioning
- 8. Y-Autoencoders: disentangling latent representations via sequential-encoding
- 9. image characteristics extraction
- 10. LARGE SCALE GAN TRAINING FOR HIGH FIDELITY NATURAL IMAGE SYNTHESIS