search

princeton-computational-imaging / NLOSFeatureEmbeddings

30 stars 10 forks source link

Detector noise #2

Open fmu2 opened 3 years ago

fmu2 commented 3 years ago

Thanks for the great work!

Would you also release the code for modeling detector noise (eq. 4 in the paper)? I am a little confused by how exactly time jitter is modeled. How many samples did you draw from the jitter distribution for each temporal bin? Thanks!

grau4 commented 3 years ago

Similar question here. I'm overall confused about how inputs are fed to the network during training (scale+Poisson+jitter), i.e the full augmentation model. I wonder if the authors plan upload a crop a training+data_load code.

wenzhengchen commented 3 years ago

Hi, sorry for the delay.

Actually we directly use code in another paper, the webpage can be found in http://graphics.unizar.es/data/spad/. They provide code. To be specific, when we use OpenGL to generate data, we treat it as clean data and next we directly apply the above code to add noise.