Not using conditional batch normalization! about convolutional_occupancy_networks HOT 5 CLOSED

Thanks so much for pointing this out @Hippogriff. Yup, I developed at the early stage directly with ONet's decoder, so forgot to change the comments. We don't use CBN at all now.

from convolutional_occupancy_networks.

@pengsongyou Hi! Thank you for your great work! I'm also very interested in why you didn't use CBN any more? Cause in ONet, CBN seems to work smoothly. Do you have any ablation study about the performance when using or not CBN in ConvONet? Or is it just an issue for GPU memory since you said "memory intensive batch normalization operation" in the paper?

from convolutional_occupancy_networks.

Hi @Wuziyi616 , thanks for your interest! We did an ablation study on this at the very beginning. We found that without CBN:

1. It is more memory efficient (I don't remember the exact number, ~20% - 30% less memory)
2. Training process becomes faster
3. We don't find any performance drop, and in some cases, it can even reach slightly higher scores with a smaller number of iterations.

Hope this helps.

from convolutional_occupancy_networks.

@pengsongyou Thank you for your quick reply! Indeed I tried the code the training is faster and converged smoothly. BTW, just to make sure, the "configs/pointcloud/shapenet_3plane.yaml" is for training the "Ours-2D (3x64^2)" on Object-Level 3D Reconstruction from Point Clouds task (in which your model achieved an IoU of 0.861) right? That performance is amazing! Again this is really a great work!

from convolutional_occupancy_networks.

Hi @Wuziyi616 , thanks for the kind word! Yup, that is the model :) I think you might even get a little bit higher score because we continue training the model for a bit longer.

from convolutional_occupancy_networks.