Open inuex35 opened 2 weeks ago
Forward pass is look okay
Iterations 7000
Iterations 30000
rendering result is not good and need to check jacobian and backward
Worked! I dont know why it's upside down.
https://github.com/user-attachments/assets/d9eff32d-0c4b-4c50-a2ed-080883eabe5e
Problem was the original dataset. It does not happen in another dataset.
Real data is not as good as simulated data, but looks working well.
https://github.com/user-attachments/assets/192cc732-d8e6-4c3e-a9eb-45e89b315388
Rendering perspective from spherical model is okay but smoky because of large floaters under ground.
Excellent contribution, I tested the code on the OmniBlender dataset and found that the default strategy has a sharp rise in loss after the 3000th step and seems to reset the opacity every 100 steps after that, resulting in a poor encounter, whereas with the mcmc strategy my psnr was 5db higher than the results on the omnigs paper!
Thank you for the validation! Indeed, some state-of-the-art functions like MCMC improve quality compared to the original implementation. I plan to try them on some datasets when I have time. If you've done any validation, please share it with everyone.
Working on spherical_render branch
Todo
Current status Forward pass is not good
Sample dataset
https://dtbn.jp/6eEZeo8e (The url will expire in a week)
image
reconstruction