Scenix framework reconstructs 3D scenes from sparse views using executable programs

Researchers have developed Scenix, a new framework for reconstructing 3D indoor scenes from a limited number of RGB images. Unlike previous methods that require extensive manual annotation or continuous visual input, Scenix predicts executable scene programs. These programs represent structured, editable 3D scenes that can be directly instantiated. The framework achieves this through perception-grounded asset instantiation and a closed-loop spatial refinement process. To support this work, a new dataset of approximately 110,000 synthetic and real indoor scenes was created, featuring multiview imagery, room structures, object descriptions, and spatial annotations. AI

IMPACT This research could enable more efficient and accessible 3D scene creation by reducing the need for extensive manual input.

RANK_REASON The cluster describes a new research paper detailing a novel framework for 3D scene reconstruction. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• arXiv
• Hugging Face
• Scenix
• SpatialGen
• XScene

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →