Luke Liu
Thank you for your outstanding work. May I ask how can we obtain the Occlusion mask ground truth of KITTI dataset for supervision? Thank you very much
Hi! Thank you for your outstanding work. I am writing to confirm the training epochs, according to the https://github.com/skyhehe123/AutoRF-pytorch/blob/master/src/train.py#L29 The training takes 100M epochs, which is quite a consuming time...
Thank you for your outstanding work! It is very impressive to deploy a diffusion pipeline into monocular depth estimation. As stated in the paper, the model works for affine-invariance depth...
I plan to add the [controlnet](https://arxiv.org/abs/2302.05543) into the original Marigold, once it have been tested, I will upgrade the code.