Baoquan Chen

Generating multi-view consistent videos with SV3D does indeed yield good results. Will the code for reconstructing 3D after obtaining multi-view consistent videos be open-sourced?

UVAtlasPartition: Non-manifold mesh，"The mesh output by Triposr does not match."

3

File "text2texture.py", line 329, in tmesh = text2texture( File "text2texture.py", line 229, in text2texture tmesh.compute_uvatlas(size, parallel_partitions=2) RuntimeError: [Open3D Error] (void open3d::t::geometry::kernel::uvunwrapping::{anonymous}::ComputeUVAtlasPartition(open3d::t::geometry::TriangleMesh, float, bool, open3d::t::geometry::kernel::uvunwrapping::{anonymous}::UVAtlasPartitionOutput&)) /root/Open3D/cpp/open3d/t/geometry/kernel/UVUnwrapping.cpp:124: UVAtlasPartition: Non-manifold mesh how to...

File "train.py", line 191, in main() File "/root/anaconda3/envs/py3-mink/lib/python3.7/site-packages/click/core.py", line 1130, in __call__ return self.main(*args, **kwargs) File "/root/anaconda3/envs/py3-mink/lib/python3.7/site-packages/click/core.py", line 1055, in main rv = self.invoke(ctx) File "/root/anaconda3/envs/py3-mink/lib/python3.7/site-packages/click/core.py", line 1404, in invoke...

standard dm的一些实现的疑问和请教

2

 大佬您论文中说的standard dm的实现，有几个具体细节想请教您，因为想复线一下： 1.您是在room上做的没在maptr上实验哈 2.我理解你说的就是训练时 standard dm的实现：相当于改变两个数值，sigma_guide = 1.0,mu_guide = 0.0,然后想请教下损失函数是没有变化吗，还是每个gt加噪的实例预测X0然后和原本这个gt的坐标算loss，因为GS-DM没有训练分类损失， standard dm也没有这部分吗 3.推理时的standard dm，按论文中说的是从标准高斯噪声采样，那么这是坐标，请问类别信息会预测吗，具体是怎么得到类别预测的呢 超级感谢大佬答疑解惑