Huan Wang
Huan Wang
@YNX940214 hi, may I ask, how many hours it takes to train the model for 50 epochs? My GPU is TitanX, it seems slow as well. Thx.
@YNX940214 okay, never mind. Thank you still.
@wenwei202 Do you mean the slow-down in GPU mode is because the `LOWERED_CCNMM` is implemented by CPU for now? If so, could you tell me how to reimplement the GPU...
Hi! we tested our method on the forward-facing real-world dataset (see visual results in the Appendix of our [1st version paper on arxiv](https://arxiv.org/abs/2203.17261v1)), which is using COLMAP to estimate the...
No, the current code does not generate a mesh.
Hi @yumath , thanks for your interest in our work! Yes, the hard masks are _not_ exactly aligned, because SSA is a regularization term, which only _encourages_ aligned masks (as...
Hi @yuanli2333 , Great thanks for your reply! It will be great to have the updated results. If on CIFAR10/100, LSR is equivalent to the proposed Tf_reg loss, that may...
Hi @nicesonnday , 600k is for the pseudo data training. For the real data finetuning, it is pretty fast and up to specific scenes (on some scenes, it only takes...
I'll close this issue given no further questions. Feel free to re-open if you see it necessary.
Hey @YouCaiJun98 , thanks for your interest in our work, and sorry for the late follow-up on this issue. The code is based on [RCAN](https://github.com/yulunzhang/RCAN), where most implementation goes back...