Giter Club home page Giter Club logo

Comments (3)

mkocabas avatar mkocabas commented on June 5, 2024

Hi @jackspp,

Thanks for your interest. The estimated camera is weak perspective, but if you assume a focal length you can convert it to perspective camera. That line is used to convert weak perspective to perspective camera. It is common to assume a fixed focal length to perform perspective projection. We borrowed that part from SPIN implementation.

from vibe.

longbowzhang avatar longbowzhang commented on June 5, 2024

Hi @mkocabas sorry to bother you again.
I have a question about the pred_camera[:, 1:3], which is used later in

points = points + translation.unsqueeze(1)
as translation added to points.
Thus I am wondering
(1) which space are pred_camera[:, 1:3] in? In other words, why not use _pred_camera[:, 1:3] * pred_camera[:, 0] as the translation[0:2]?
(2) what is the reason behind setting translation[2] = pred_cam_t[:, 0], why move points in the z direction?

from vibe.

lvZic avatar lvZic commented on June 5, 2024

Hi @jackspp,

Thanks for your interest. The estimated camera is weak perspective, but if you assume a focal length you can convert it to perspective camera. That line is used to convert weak perspective to perspective camera. It is common to assume a fixed focal length to perform perspective projection. We borrowed that part from SPIN implementation.

Hi @mkocabas sorry to bother you again.
I found the cam params converge worse, and i use weak perspective in my code, in which kpy_2d = scale(kyp3d[, :2] + txy ). I think the key reason is the focal length of the dataset is different with each image, and it range from 400 mm to 800 mm. So maybe the network cannot regress the scale well?
As u said "It is common to assume a fixed focal length to perform perspective projection. " . I wonder if the performance would be improved if i use perspective projection instead of weak perspective?

from vibe.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.