Segment Anything in 3D with NeRFs

Feb-19-2026, 11:24:50 GMT–Neural Information Processing Systems

We refer to the proposed solution as SA3D, for Segment Anything in 3D. It is only required to provide a manual segmentation prompt ( e.g., rough points) for the target object in a single view, which is used to generate its 2D mask in this view with SAM.

machine learning, natural language, segmentation, (19 more...)

Neural Information Processing Systems

Feb-19-2026, 11:24:50 GMT

Conferences PDF

Add feedback

Country:
- Asia
  - China > Shanghai
    - Shanghai (0.04)
  - Japan > Honshū
    - Chūbu > Ishikawa Prefecture > Kanazawa (0.04)

Genre:
- Research Report (0.46)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning > Neural Networks
      - Deep Learning (0.46)
    - Natural Language (0.68)
    - Vision (1.00)
  - Sensing and Signal Processing > Image Processing (0.68)

Duplicate Docs Excel Report

Title
Segment Anything in 3D with NeRFs

Similar Docs Excel Report more

Title	Similarity	Source
None found