AI葵

icon indicating a website link https://www.youtube.com/channel/UC7UlsMUu_gIgpqNGB4SqSwQ icon indicating an email [email protected]

icon company Luma AI icon location Taipei icon location AI R&D in computer vision. Doing VTuber about DL algorithms. Check my channel! If you find my works helpful, please consider sponsoring! 我有在做VTuber，歡迎訂閱我的頻道！

Results 152 comments of AI葵

About the FPS on the MipNerf360 dataset in the original paper.

There is A6000 Ada (faster) and A6000. Maybe they mean the faster one

eval isotropic in the code

1. remove the `.repeat(1, 3)` on this line (so that `self._scaling` is a (N, 1) tensor) https://github.com/graphdeco-inria/gaussian-splatting/blob/2eee0e26d2d5fd00ec462df47752223952f6bf4e/scene/gaussian_model.py#L135 2. add `.repeat(1, 3)` to the end of this line https://github.com/graphdeco-inria/gaussian-splatting/blob/2eee0e26d2d5fd00ec462df47752223952f6bf4e/scene/gaussian_model.py#L97 in this...