2 datasets found

Tags: 3D Visual Grounding

Filter Results

  • ScanERU

    A semi-synthetic dataset for 3D visual grounding task, covering semi-synthetic scenes with textual, real-world visual, and synthetic gestural information.

  • ScanRefer

    ScanRefer is a dataset of 51,583 referring descriptions of 11,046 objects from 800 ScanNet scenes.
You can also access this registry using the API (see API Docs).