Blog
About

68
views
0
recommends
+1 Recommend
0
shares
    • Review: found
    Is Open Access

    Review of 'Few-Shot Adversarial Learning of Realistic Neural Talking Head Models'

    Bookmark
    5
    Few-Shot Adversarial Learning of Realistic Neural Talking Head Models
    A system for meta-learning on large datasets of videos is presented
    Average rating:
        Rated 5 of 5.
    Level of importance:
        Rated 5 of 5.
    Level of validity:
        Rated 5 of 5.
    Level of completeness:
        Rated 5 of 5.
    Level of comprehensibility:
        Rated 5 of 5.
    Competing interests:
    None

    Reviewed article

    • Record: found
    • Abstract: found
    • Article: not found
    Is Open Access

    Few-Shot Adversarial Learning of Realistic Neural Talking Head Models

    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.
      Bookmark

      Review information

      10.14293/S2199-1006.1.SOR-COMPSCI.A1905.08233.v1.RIDRIL

      This work has been published open access under Creative Commons Attribution License CC BY 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Conditions, terms of use and publishing policy can be found at www.scienceopen.com.

      ScienceOpen disciplines:

      Review text

      The presented approach is able to learn highly realistic and personalized talking head models of new people and even portrait paintings.

      Comments

      Comment on this review