search

JasonQSY / 3DOI

[ICCV 2023] Understanding 3D Object Interaction from a Single Image
35 stars 2 forks source link

if there is any plans to release the code of AffordanceLLM #2

Open vvvvvjdy opened 2 weeks ago

vvvvvjdy commented 2 weeks ago

apologize for the questions about your another significant work . really appreciate your work AffordanceLLM: Grounding Affordance from Vision Language Models and this 3DOI about the breaking contribution in Visual Affordance aspect. I want to use your model and training strategy of AffordanceLLM: Grounding Affordance from Vision Language Models as my new baseline. Would you have any plans about releasing the code of AffordanceLLM. Cant wait to have a try! Appreciate a lot！

JasonQSY commented 2 weeks ago

Thanks for your interests in our work!

Unfortunately, I don't have the code and checkpoint right now. It is my Amazon internship project, and the code and checkpoint have not been released by Amazon. A few suggestions: (1) If you want to build a similar approach, LISA might be a good codebase to start with. https://github.com/dvlab-research/LISA I can help with implementation details as well. (2) The benchmark has been released on the project page https://jasonqsy.github.io/AffordanceLLM/

vvvvvjdy commented 2 weeks ago

Appreciate for your help ! I will try to start!