Ruilong Li(李瑞龙)

Hi unfortunately we don't support combining the coarse and fine sampling

Hi I think in this case you should not use the auto aabb, which is computed from the min max camera locations. You might want to set up a AABB...

Are you using our example script with `auto_aabb` enabled?: https://github.com/KAIR-BAIR/nerfacc/blob/1bc23a180eae1bacfd2ed5452b46f2939f776942/examples/train_ngp_nerf.py#L125-L132

That is what I was saying, you might want to set up a suitable aabb in this case, instead of using this auto aabb which is just the min max...

It is directly sampled from t-space. We followed the way of sampling from NGP.

Hi the neus is a 3rd party impl. I didn't play with neus myself so have no intuition on this. I think it should not be too hard to play...

SG! Would be curious to see the difference.

You can take reference from this impl of neus with nerfacc: https://github.com/bennyguo/instant-nsr-pl/blob/215274e2f99d2481ba00f3345fe3f3dd1b9c3d74/models/neus.py#L49-L60 Or, you can take reference from our example here: https://github.com/KAIR-BAIR/nerfacc/blob/488bca66fc05b5bff5982170f204052e75ae2a67/examples/train_ngp_nerf.py#L193-L208, where we calculate view-dependent step size on the...

@miaojiang1987 Sorry for the delay and thank you for pointing this bug. I've fixed it and update the repo by modifying Line 449. in `train.py`.

@muni2773 LIP means ['Look Into Person'](http://sysu-hcp.net/lip/) and ATR comes from [here](https://github.com/lemondan/HumanParsing-Dataset)