How fast is the training process of 3D field and autoencoder?

minghanqin / LangSplat

Official implementation of the paper "LangSplat: 3D Language Gaussian Splatting" [CVPR2024 Highlight]

https://langsplat.github.io/

Other

674 stars 72 forks source link

Closed jeezrick closed 10 months ago

jeezrick commented 10 months ago

~~Great paper.Can the autoencoder be trained in real-time？ Or is the usage scenario of this model limited by the scene-wise language autoencoder? ~~

Never mind, stupid question.

What I really want to know is, how fast is the training process from a set of image to the language 3D field?

And how much of images needed?

I am wondering if this method can be applied to real time robot navigation.

minghanqin commented 10 months ago

Hi,

Thank you for your attention!

We have released the code of autoencoder.

For a scene with 1080p resolution, our model is trained for 25 minutes on an NVIDIA RTX-3090 GPU.