Youtian Lin comments

Results 8 comments of


                                            Youtian Lin

Add support for frexp() function

Thanks for the great work!

Dispatch error when using Vulkan backend on Intel integrated graphics

Hi~ @victoriacity I don't have an intel integrated GPU to test this issue, but according to the log messages, the error appears when `from_numpy` is called. Could you write another...

OSX M1Max not able to render

Hi @tlightsky So, it looks like the problem could be because of Taichi 1.6. I'll dig into it and try to fix it ASAP. You could use the older version...

fix & speedup show_gui

> how much speed up do you get by switching `dearpygui` to `taichi`? I get a 2-3 fps increase in the Lego scenes after switching to `taichi`, but the movement...

Does taichi-ngp renderer support training nerfs?

Hi @dhombios, taichi-ngp currently only supports rendering, not training. To render a new scene, you'll need to train your model using [ngp_pl](https://github.com/kwea123/ngp_pl) or other PyTorch implementations and convert it using...

[Feat req] Nerf->SDF->Mesh pipeline for AIGC

Hi @yhyu13 Thanks for bringing this up! Regarding your question, I currently do not have any plan to support mesh extraction. However, you could consider using another repo like [nerfmesh](https://github.com/qway/nerfmeshes),...

grad_scaler.scale(loss).backward

Hi @lixinhaiyk! Could you please share your environment information, such as the version of taichi and GPU? Please note that the current version of taichi-nerfs requires taichi-1.6, so ensure that...

Upload datasets as Github artifacts

Hi @ahojnnes @skoppula, Thanks for the suggestion. We’ve also noticed the OneDrive issue for the + and ++ extensions, so we’ve added GitHub release links for both. - BlendedMVS1 is...