Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

map_pdf_to_opacity #73

Open
jiho314 opened this issue Mar 19, 2025 · 0 comments
Open

map_pdf_to_opacity #73

jiho314 opened this issue Mar 19, 2025 · 0 comments

Comments

@jiho314
Copy link

jiho314 commented Mar 19, 2025

Hi thank you for your great work!

Could you please explailn why did you use pdf with warming up? Also I'm curious about the reference of the equation.

src.model.encoder. encoder_nopo_splat:

map_pdf_to_opacity

  def map_pdf_to_opacity(
        self,
        pdf: Float[Tensor, " *batch"],
        global_step: int,
    ) -> Float[Tensor, " *batch"]:
        # https://www.desmos.com/calculator/opvwti3ba9

        # Figure out the exponent.
        cfg = self.cfg.opacity_mapping
        x = cfg.initial + min(global_step / cfg.warm_up, 1) * (cfg.final - cfg.initial)
        exponent = 2**x

        # Map the probability density to an opacity.
        return 0.5 * (1 - (1 - pdf) ** exponent + pdf ** (1 / exponent))
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant