How to render results with weak perspective camera
See original GitHub issueThanks a lot for this great and easy-to-use repo!
I’m trying to render the results using the weak perspective camera model. My question relates to these issues:
- https://github.com/Arthur151/ROMP/issues/134
- https://github.com/Arthur151/ROMP/issues/241
- https://github.com/Arthur151/ROMP/issues/300
However none of these issues gave me the answer I was looking for. I am using the weak perspective camera parameters stored in cam
and as suggested in this issue I multiply them with 2. I also pad the image to be square as mentioned here. I then convert the weak perspective camera model to a projection matrix the same way I used to do it for VIBE, which worked well there. However, for the ROMP output I’m still getting a slight misalignment, as you can see in the following screenshot. The light model is what I am rendering and the blue model in the background is the visualization output from ROMP. I think it’s because I should somehow account for cam_trans
but I don’t know how exactly. Can you help me with this?
Issue Analytics
- State:
- Created a year ago
- Comments:11 (4 by maintainers)
Top GitHub Comments
@Arthur151 Amazing! Please let me know (probably best via Github issues) if you encounter any problems or if you have feature requests that would make things easier for you!
Thanks! @kaufManu I am really impressed by the latest (plentied of) new features, especially the visualization with camera and image demo. I am re-formulating the whole visualization pipeline with your AITViewer. Hope I can update this part in the next work. Best regards, Yu