LayoutNet

LayoutNet copied to clipboard

Max pooling is directly followed by upsampling

1

The network's structure contains max pooling immediately followed by upsampling. Maybe I'm missing something but it doesn't seem to make any sense. And just removing it should improved results. local...

jackaceuser

3D ground truth interpretation

2

Hello, First, thank you for sharing this great work. A quick question about the panoContext_box_train.t7 tensor: The paper mentions 6 ground truth 3D parameters: sw, sl, sh, tx, tz, r_theta....

teasherm

What is the ground-truth mask used during training?

1

Hi I saw in the file train_pano_joint.lua that you use somekind of mask to increase the loss at some poisitions. I couldn't find any reference to that neither in the...

jackaceuser

Would you mind share the code about perspective images?

11

Mingyangliiiiii

I want to make to iOS app using Core ML :)

2

Hi! It’s awesome idea! I’m iOS developer and want to make to iOS DEMO! Is there a trained model? (Sorry for bad English)

tucan9389

Could you also share the code of generating Manhattan lines?

1

yangli5t