Skip to main content

All Questions

0 votes
0 answers
12 views

Question about bpy's matrix_world to torch3d coordinate system conversion

From the visualization results, it appears that the camera pose I converted is not accurate. It has moved backwards. Is there have any suggestions ?QAQ 1.difference of cameras space 2 some discussion
Haitao Xiao's user avatar
6 votes
1 answer
448 views

Finding image coordinates of rendered vertex after refraction, distortion, etc

I'm in blender 2.92 working with the Python API. I know how to get the pixel coordinates of a vertex before refraction, lens distortion, etc.--see e.g. How to find image coordinates of the rendered ...
jmetzger's user avatar
0 votes
1 answer
809 views

How to map/project bone coordinates to camera coordinates sytem/view?

I need the bone-head coordinates to be mapped on to the camera view. Actual scenario is to obtain the 3D coordinates of bone/joint. This is how I do it now. ...
p.Neu's user avatar
  • 61
3 votes
0 answers
1k views

How to find if the vertex of an object is occluded by another vertex/face in front of it from a given viewpoint?

I can use the recipes on this page: How to find image coordinates of the rendered vertex?. But is there a way to know if a point is being occluded by some point/face in front of it from the viewpoint ...
web_ninja's user avatar
4 votes
1 answer
2k views

How can I get the projection matrix of a panoramic camera with a fisheye equisolid lens?

I am working on a project in which i used the panoramic camera with fisheye equisolid lens on Cycles render. For some tests, I need the projection model that uses by this camera to project a 3D point ...
BetterEnglish's user avatar
3 votes
1 answer
3k views

blender camera from 3x4 matrix

In computer vision, the transformation from 3D world coordinates to pixel coordinates is often represented by a 3x4 (3 rows by 4 cols) matrix P as detailed below. Given P I need code to return a ...
rfabbri's user avatar
  • 1,243
29 votes
2 answers
33k views

3x4 camera matrix from blender camera

In computer vision, the transformation from 3D world coordinates to pixel coordinates is often represented by a 3x4 (3 rows by 4 cols) matrix P as detailed below. Given a camera in Blender, I need ...
rfabbri's user avatar
  • 1,243