Page cover image

👁️IRON

IRON: Image geneRation for Open-world object rearraNgement

  • Led a team to implement a pipeline for image generation for open-world object rearrangement with Mask R-CNN, OFA, CLIP, DALL-E 2, Hanlp, by first inferring a text description of those objects, then generating an image representing a natural, human-like arrangement for the objects. It can be integrated with robots to rearrange objects physically.

https://github.com/Skevinci/iron

Last updated