-
Notifications
You must be signed in to change notification settings - Fork 15
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
Questions about relighting effects #5
Comments
Hi, thank you for your interest in the project! The method was designed primarily for outdoor scene relighting, and we didn't test it on indoor scenes ourselves. Again, it's quite exciting to see NeRF-OSR almost working on the indoor scenes. Best, |
Also it seems like the rendered image is cropped a bit. Also it seems like the rendering camera poses for the videos were generated using |
Thanks for your reply! |
During the test, your technique can synthesise novel images at arbitrary camera viewpoints and scene illumination; the user directly supplies the desired camera pose and the scene illumination, either from an environment map or directly via SH coefficients. |
Hi, I also think this is wonderful work for generating novel views and relighting images from an optimized neural network. However, i also have a similar issue that is the NeRF takes the default values as the env param of testing or validating images and does not optimize them it, so ..... if this, the validation images or test images have no means. Although, I also agree that this work is very inspired me!!! |
Hi. Thank you for the kind words! You can change environments used for testing with Default value for the environment is taken from one of the runs of the method on our data. When we used completely random inialisation values, the model often diverged. Using these coefficients instead resulted in more consistent and better training results on the tested scenes. Coincidentally, they are also used for rendering views where no other envmap is found, which are validation and test views (when To use an external LDR/HDR envmap, you would first need to convert it to SH coefficients. The conversion will just fit the closest SH coefficients with least squares. The script for that is not yet in the repo, but I'll upload it soon, as well as the instructions on how to reproduce our numerical results from the paper. The latter involves using external environment maps and this SH conversion step too, so it should be helpful. |
The algorithm does not have an ideal effect on the indoor dataset.
As shown in the figure below, the effect of relighting is not very good. There is a "hole" on the surface of the chair.
I guss this is due to some inaccuracies in geometry estimation.
I would appreciate it if receiving your reply.
@r00tman
ori_img:
![image](https://user-images.githubusercontent.com/114200977/200469435-b07dffbf-edad-44bf-bc53-76af343712ad.png)
relighting:
![000000](https://user-images.githubusercontent.com/114200977/200470259-f660d7b1-9c6f-4e87-9394-5b1ade25cb51.png)
![000046](https://user-images.githubusercontent.com/114200977/200470019-db893e28-6d9d-45de-b4e7-aaa91a210a90.png)
![fg_normal_000046](https://user-images.githubusercontent.com/114200977/200470077-00fb8e34-e93d-4323-89a3-488fd05db579.png)
The text was updated successfully, but these errors were encountered: