按年被提到
20192019 · 7 次2026
视觉、语音与图像生成›生成对抗网络·arXiv:1905.08233 · cs.CV

Few-Shot Adversarial Learning of Realistic Neural Talking Head Models

Egor Zakharov, Aliaksandra Shysheya, Egor Burkov, Victor Lempitsky · 2019
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 7 人首次 2019-05-23 · 最近 2019-07-07
7不同的人
2活跃月份
7讨论串
683被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Several recent works have shown how highly realistic human head images can be obtained by training convolutional neural networks to generate them. In order to create a personalized talking head model, these works require training on a large dataset of images of a single person. However, in many practical scenarios, such personalized talking head models need to be learned from a few image views of a person, potentially even a single image. Here, we present a system with such few-shot capability. It performs lengthy meta-learning on a large dataset of videos, and after that is able to frame few- and one-shot learning of neural talking head models of previously unseen people as adversarial training problems with high capacity generators and discriminators. Crucially, the system is able to initialize the parameters of both the generator and the discriminator in a person-specific way, so that training can be based on just a few images and done quickly, despite the need to tune tens of millions of parameters. We show that such an approach is able to learn highly realistic and personalized talking head models of new people and even portrait paintings.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论fromthestart · 2019-07

“You train the neural net to encode landmarks which are unique to individual faces. Such a net, when trained, can extract the unique facial features from a single image and embed them in a vector to be compared to features extracted from other images. This is similar to how single images of faces can be animated with GANs now. https://arxiv.org/abs/1905.…”

FBI, ICE using state driver’s license photos for facial-recognition searches原评论 ↗
被提交为 story · 6 次