8000 2D Landmarks from FLAME model · Issue #31 · andresprados/SPIGA · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
2D Landmarks from FLAME model #31
Open
@emlcpfx

Description

@emlcpfx

Hi, I have really a really strong 3D track of a FLAME model on some footage.
https://www.linkedin.com/posts/ericlevy_were-doing-rd-on-a-new-machine-learning-activity-7262912859997716481-D4Do?utm_source=share&utm_medium=member_desktop

How can I derive the 2D landmarks from this like how SPIGA does, where they follow the contour of the face?

Could I use the pose data from the other repo to replace the pose data that SPIGA comes up with, and get a better result?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions

      0