How to reconstruct environment map?

fnzhan / EMLight

[AAAI 2021] EMLight: Lighting Estimation via Spherical Distribution Approximation, [TIP] GMLight: Lighting Estimation via Geometric Distribution Approximation

168 stars 35 forks source link

How to reconstruct environment map? #22

Open xqwang14 opened 1 year ago

xqwang14 commented 1 year ago

envmap

I tried both train and test code on Laval Indoor dataset, and from the test code, I get one result as the image shown above. It seems like the Guassian Map that mentioned in the paper, and I wonder how to reconstruct the environment map from this image.

Thank you so much for your excellent work and I look forward to any reply.

fnzhan commented 1 year ago

A generation network is followed to translate gaussian map to illumination maps, i.e., GenProjector. The generation network is highly biased to the training scene, I recommend you to train it with your data.

najmemhmdb commented 1 year ago

To use GenProjector, I need latest_net_G.pth file. Could you please share its weights with me?

Thank you.

ad45675 commented 1 year ago

hi @a978908609 ,

when i run the training code , i got some error,

Traceback (most recent call last): File "train.py", line 97, in dist_emloss = Sam_Loss(dist_pred, dist_gt).sum() 1000.0 File "/venv/py37_zero-XRWy4lKA/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1051, in _call_impl return forward_call(input, **kwargs) TypeError: forward() missing 1 required positional argument: 'geometry' so you have use the geometry in the training?