Frozen LM for object-level grounding

scene-verse / SceneVerse

Official implementation of ECCV24 paper "SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding"

https://scene-verse.github.io

MIT License

197 stars 3 forks source link

Frozen LM for object-level grounding #15

Closed sayands closed 3 months ago

sayands commented 4 months ago

Hi, firstly thanks for your nice work! I was curious to know which frozen Language Model did you use for object-level grounding, as mentioned in Sec 4.1 of the paper?

Please let me know. Thanks!

Buzz-Beater commented 3 months ago

We used a frozen bert-model for pre-training the alignment between pcd object encoder and language model.