Open buaacyw opened 1 year ago
Could you please share the cmd line to generate the result above? Besides, i find that, at least in my experiment, NaN is mainly caused by grid encoder. DMTet actually can't model large shape compared to NeRF
The cmd: Fig 1: python main.py --text "a hamburger" --workspace trial -O python main.py -O --text "a hamburger" --workspace trial_dmtet --dmtet --iters 5000 --init_with trial/checkpoints/df.pth # load the ckp of the first cmd Fig 2: You need to add a scaler to the lr of the sdf and deform value of DMTET. And than the cmd is the same with Fig 1 except the lr scaler Fig 3: the mid result of python main.py --text "a hamburger" --workspace trial -O Only train about 500 steps Fig 4: load the ckp of Fig3 and than change the prompt to pineapple: python main.py -O --text "a pineapple" --workspace trial_dmtet --dmtet --iters 5000 --init_with trial/checkpoints/df.pth
Could you please share the cmd line to generate the result above? Besides, i find that, at least in my experiment, NaN is mainly caused by grid encoder. DMTet actually can't model large shape compared to NeRF
Hi! How did you find the Nan is caused by grid encoder? There is also some Nan in sds loss. It seems that what we can do is to just ignore the Nan? I agree that DMtet can't learn large shape.
Hi! Thanks a lot for this repo! I find that finetune with DMTET works well for color but only brings tiny changes to the geometry. I hope to also refine the geometry largely with DMTET. There are several scenes that this might be useful:
I tried to enlarge the lr of DMTET parameters (vertex sdf and deformation). With all other settings and lr unchanged, I get a better result by using a 10 times larger lr for DMTET parameters. The first one is Hamburg generated with the default DMTET setting in Readme guide. And the second one is trained with ten times DMTET lr. However, the model collapses with 100 times lr.
![84b576ed42c6494b9c039308acfb87b](https://github.com/ashawkey/stable-dreamfusion/assets/52091468/fbc23ddc-d124-43d3-8984-6669c0886ce3)
I also tried to finetune a hamburger to pineapple by changing the prompt from "a hamburger" to "a pineapple" when training with DMTET. With the first image as init, I find the geometry of the result (second image) still doesn't change with the changed prompt.
![492f4ee5b1a8742cc068bd003da0505](https://github.com/ashawkey/stable-dreamfusion/assets/52091468/26b5fde6-88ad-4d45-a654-7c0bb776095e)
I'm curious about why is this happing. Shouldn't DMTET make geometry changes easier since it provides a more efficient 3D representation? I have checked the gradient for vertex sdf and deformation. I find lots of nan in the grad. But this repo didn't use transform these nans to zeros. Will these nans cause some problems?