Segment 3D object using 2D instance masks from RGB-D frames with Open3DIS
Segment 3D object using 2D instance masks from RGB-D frames with Open3DIS
Open3DIS: Open-vocabulary 3D Instance Segmentation with 2D Mask Guidance
arXiv paper abstract https://arxiv.org/abs/2312.10671
arXiv PDF paper https://arxiv.org/pdf/2312.10671.pdf
Project page https://open3dis.github.io
... introduce Open3DIS, a novel solution designed to tackle the problem of Open-Vocabulary Instance Segmentation within 3D scenes.
... Recent advancements ... employing class-agnostic 3D instance proposal networks for object localization and learning queryable features for each 3D mask.
While these methods produce high-quality instance proposals, they struggle with identifying small-scale and geometrically ambiguous objects.
The key idea of ... method is a new module that aggregates 2D instance masks across frames and maps them to geometrically coherent point cloud regions as high-quality object proposals addressing the above limitations.
These are then combined with 3D class-agnostic instance proposals to include a wide range of objects in the real world.
... approach ... demonstrating significant performance gains in segmenting objects with diverse categories over the state-of-the-art approaches.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments