InseRF
I
Inserf
Overview :
InseRF is a method for generating new 3D objects within NeRF-reconstructed 3D scenes using text prompts and 2D bounding boxes. It can create a new 3D object from user-provided text descriptions and a 2D bounding box in a reference viewpoint, then insert it into the scene. This method enables controllable and 3D-consistent object insertion without requiring explicit 3D information. Experiments on multiple 3D scenes have demonstrated the effectiveness of the InseRF method compared to existing approaches.
Target Users :
Insert new objects into 3D scenes.
Total Visits: 17
Top Region: TH(84.62%)
Website Views : 65.4K
Use Cases
Insert new furniture decor in a 3D interior scene
Insert new buildings or props in a city scene
Insert new plants or scenery in an outdoor landscape
Features
Generate new 3D objects from text prompts and 2D bounding boxes
Convert generated 2D edits into 3D object models
Place and merge generated 3D objects within a scene
Perform optional refinement to further improve appearance
AIbase
Empowering the Future, Your AI Solution Knowledge Base
© 2025AIbase