A vision-language framework predicts editable JSON-like 3D scene programs from a few uncalibrated RGB views, and a new 110K-scene dataset supports training.
European Conference on Computer Vision , pages=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Scenix: Sparse-View 3D Scene Reconstruction via Executable Scene Programs
A vision-language framework predicts editable JSON-like 3D scene programs from a few uncalibrated RGB views, and a new 110K-scene dataset supports training.