Qianli Ma
Qianli Ma
Can you post the error message?
It depends on how big is the domain gap of your data from what we trained on. Currently POP is trained on clean, full point clouds (i.e. complete, without holes...
Hi, did you try install the chamferdistance package as mentioned in the README? 
Hi, in principle the process is the same as that link in SCALE; i.e. first fit a SMPL/SMPLX model to the scan, repose the fitted body model to the desired...
Hi, sorry for my late reply. Here's a quick how-to in case you need it urgently. To get the vtransf, we modified the smplx package a bit: in [lbs.py](https://github.com/vchoutas/smplx/blob/cfa54f8135ca6cb8b3588c2d893a4df7a94032ed/smplx/lbs.py), this...
> You can use [this code](https://github.com/qianlim/SCALE/blob/main/lib_data/posmap_generator/apps/example.py) (the variable "uv_mask" is what you need) in the SCALE repo to generate the UV map at arbitrary resolution. For that you simply need...
Hey guys! @fishfishson is right: my latest commit fixed a bug in the original code (= where all the pre-trained checkpoints are based on, also = the model that are...
Hi, if you mean the colored ('with texture') point set in the teaser, when the GT point color is available, we train a model that predicts the normals and point...
Right, the CAPE meshes contain only geometry but no texture. As the training data of SCALE is actually sampled point clouds from the CAPE mesh surfaces, what we did is...