wbhu/mono3d

Source code for "Mononizing Binocular Videos" (SIGGRAPH Asia 2020)

Hi there 👋

mono3d's Issues

Training code

In scripts/train.sh it seems to be running a train.py file, but I cannot find such file. Do you have any plans to release this file in the future?

Training for Video

You mention that you pass P_t-1 to the reconstructor at time t similar to an RNN. Do you use the same architecture as an RNN, in that you have a learnable linear layer that multiplies P_t-1 and then sum the result with P_t and this is what is passed onto the reconstructor?

CNS module in image version model

Thanks for your valuable work!
I would like to know that whether the CNS module is used in the image version model? How to embed this module in the code? Could you offer a demo for this? Thanks for your time!

Path Issue?

Whenever I try to run the demo
$ python main/demo.py --left ./imgs/demo_L.png

I get the error
No module named base.baseTrainer

It seems like the file cannot properly import the file inside base.

Also, I want to ask about the environment. In the README, it mentioned env.yaml, but I cannot seem to find the file.

CNS Module

Would it be possible for you to describe how the CNS is implemented, specifically the macroblock jitter.

Mono3D Video Loss Function

You mentioned that you use a RNN version for stereo video input. However, how is the loss calculated. The formula provided is lambda_1 * MonoLoss + lamba_2* InverseLoss + StereoLoss. Are the losses added per time-step? Then loss.backward() is performed at the end of the batch?