Chen Wang
I have successfully run the lmoWonder3D data. But still find it hard to run on real custom data (only have one image and its mask), the current dataloader is strongly...
Looking forward to the code!
The GT image is 252x189 in this case and subpixel rays are divided at the resolution of 504x378. 504x378 images are not used for supervising the training, i.e. self.all_rgbs_ori are...
C(r) in the loss function is self.all_rgbs. Remember that self.all_rays and self.all_rgbs are different in dimension, the former is (252x189, 2x2, 3) and the latter is (252x189, 3). You can...
No. We only need low resolution images to train. I start with 504x378 images because I can directly sample 504x378 ray directions in this way, but we can also sample...
You can directly use an empty image to get 504x378 rays. I recommend you to run the code and see how it works :)
Hi, the psnr for ficus is 26.635. I htink the fine_psnr_ori_val_full is only evaluated on one view, not the full scene.
How did you get the PSNR? On all images?
That's weird. The training script looks ok to me, I can try to find my previous checkpoints, but it may take some time.
Also interested in this