Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting

Nov-19-2025, 18:14:09 GMT–Neural Information Processing Systems

In detail, we utilize foundation visual perception models to obtain each generated object from the image and leverage pre-trained depth estimation models to lift the generated 2D image to 3D space.

arxiv preprint arxiv, large language model, machine learning, (19 more...)

Neural Information Processing Systems

Nov-19-2025, 18:14:09 GMT

Conferences PDF

Country:
- Asia > China
  - Shanghai > Shanghai (0.04)
- North America > United States
  - Massachusetts > Middlesex County
    - Cambridge (0.04)
  - Pennsylvania > Allegheny County
    - Pittsburgh (0.04)

Genre:
- Research Report
  - Experimental Study (1.00)
  - New Finding (0.67)

Industry:
- Education > Educational Setting (0.46)

Technology:
- Information Technology
  - Artificial Intelligence
    - Machine Learning > Neural Networks (1.00)
    - Natural Language > Large Language Model (0.72)
    - Representation & Reasoning > Constraint-Based Reasoning (0.68)
    - Robots (1.00)
    - Vision (1.00)
  - Sensing and Signal Processing > Image Processing (1.00)