Jiale Xu
Jiale Xu
@1999kevin Hi, have you solved the problem? I'm also trying to use Meshlab to simplify the meshes and find that it produces non-watertight meshes with holes. Do you have some...
I'm sorry but we haven't tested on older pytorch or CUDA versions. It seems that using older pytorch version (
默认生成的是带顶点颜色（vertex color）的obj文件，可以尝试使用`run.py`并指定`--export_texmap` flag生成带有texture map的obj文件。
@eastone11 You mean multi-view reconstruction? It is a good idea, but our reconstruction model also needs the camera poses as input, so we need both the pictures and their poses....
It's indeed due to the unsatisfying human body/face generation capability of Zero123++, which leads to distortions and multi-view inconsistency. Please try using front-view images as input.
huggingface上用的是instant-mesh-large
We cannot provide any help since there is not enough information.
@kunalkathare Hi, as we have stated in the README file, we provide our training code only to facilitate future research and we cannot provide our training dataset due to its...
@wenqsun @kunalkathare We render our dataset following the setting of LRM. To be specific, each 3D model is normalized into a unit cube in the range of [-1, 1]. We...