search

autonomousvision / differentiable_volumetric_rendering

This repository contains the code for the CVPR 2020 paper "Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision"
http://www.cvlibs.net/publications/Niemeyer2020CVPR.pdf
MIT License
798 stars 90 forks source link

How to obtain world / camera / scale matrix #24

Closed tau-yihouxiang closed 4 years ago

tau-yihouxiang commented 4 years ago

Thank you for the provided dataset! However, I don't know how to calculate the provided world / camera / scale matrix. The original dataset set camera mode as "look at" which consists of azimuth, elevation and distance.

m-niemeyer commented 4 years ago

Hi @tau-yihouxiang , thanks a lot for your message!

Please have a look at the newly created FAQ: https://github.com/autonomousvision/differentiable_volumetric_rendering/blob/master/FAQ.md

Thanks a lot!

tiexuedanxin commented 3 years ago

Thank you for the provided dataset! However, I don't know how to calculate the provided world / camera / scale matrix. The original dataset set camera mode as "look at" which consists of azimuth, elevation and distance.

hello, do you know how to obtain world / camera / scale matrix, I want to perform some additional test on my own dataset to do multiview reconstruction , but I don't know how to create dataset such as how to calculate the world / camera / scale matrix. Could you give me some advice on how to do it, thank you.