VLadImirluren

I saw you compare the depth estimation with pixel nerf and ibrnet. I also interested in depth estimation with other nerfs. Did you compare with others? Can you share some...

How can I define the bouding box? like llff : self.scene_bbox = torch.tensor([[-1.5, -1.67, -1.0], [1.5, 1.67, 1.0]]). But I really don't know what exactly it is or how big...

I can use COLMAP create LLFF successfully, but I can't understand how to do next. Can you explain it to me in more detail？ thanks!! 

thanks for your good reproduction!! I noticed that when exp_iter_ratio

about train zero123

6

I see the images in logs, but I don't understand what exactly is of the five picture below. train/conditioning train/inputs train/reconstruction train/samples train/samples_cfg_scale_3.00 Can you give me a introduction of...

Thanks to your great implementation! I have a question about VQ-VAE. The paper of VQ VAE says that argmin of Ze and ej is measured using L2 distance. You implementation...

memory cost

2

I haven't as large compute resource as yours. This make me hard to reproduce your work. Can you share some trick of reduce the memory cost but reach the same...

reproduce problem

11

 I use your house geometry and apperance on 4 * 4090, but still meet problem. How can I solve.. Thanks

config help

3

I want a "A candle made of silver", It is an example in TANGO, another work of you. I want to see it in Fantasia3D, can you help me? Thanks...

Thanks to your great code~ Could you give more guidance about using the torch version to TPS the image? Thanks