Brans

Bad results

12

Thank for the work. I have run the modules according to the read me, but most of results after the TOM stage ('try-on' generated folder) contains significant artifacts. Just attaching...

How to markup custom dataset?

1

Hi! What is a procedure to markup a custom dataset?

Samples count

3

Hi! How much samples did you use to train the network? What was the huber loss? Can You share the training data to play with it and compare with my?...

Is Scene box working correctly?

2

I have noticed that changing `scene_box = SceneBox(aabb=torch.tensor([[-1.5, -1.5, -1.5], [1.5, 1.5, 1.5]], dtype=torch.float32))` in the blender_dataparser.py to `scene_box = SceneBox(aabb=torch.tensor([[-.005, -.005, -.005], [.005, .005, .005]], dtype=torch.float32))` does not affects...

Some toy, simple dataset

2

Work with 256 gb dataset is very, very inconvenient. It will be so great to have some toy, small dataset. Maybe 3d generated. Maybe someone has such kind of dataset...

Can I add my retriever api?

3

Can we add custom retrievers? (closed source with api)

Hi! I see you are using upsampling operator `(torch.nn.Upsample(scale_factor=2,mode='bilinear') ` after the “Convert to RGBA” block. (LGD iteration 1 after the initialization step). Don't see this part in the paper....

Hi. Do you have some code, example or a pattern for extending an existing video?