XLR-man

Did you solve it?

Thank you for your reply! I have tried you suggestion，however，i still can't get pleasurable results. Unlike the above, the enhanced image will show large area artifacts in grass green color....

By the way, I found when add enhancement losses, after roughly 1k iterations, the enhancement losses will be nan. And I also found that the value of enhanced image very...

Update！ Now the main problem is that the reconstruction based on r and v works well, but once the enhanced loss function is added to the constraint, it will fail,...

When I remove loss_cc for training, the enhancement result is:  In addition, is your model trained on a single gpu and does not support multi-GPU training? I found that...

I found that this seems to be the case for multi-GPU training, but not for single-GPU training. Why is that?

I have changed my custom datasets which are colmap data format to .torch files. And when i test it, it got an error: ``` Traceback (most recent call last): File...

You said GT images are 252×189 resolution images, so C(r) in the loss function is self.all_rgbs? Does the color of the second dimension by averaging self.all_rays and subtracting self.all_rgbs constitute...

Ok, I get the idea. So does this mean that if we only have low resolution images, like 252×189 but not 504×378, then we can't train?

So why would you downsample a 504×378 resolution image to 252×189 resolution? You mean that only 252×189 resolution images can be trained, but self.all_rays of 252×189 resolution images should not...