ShellMaker generates complete building exteriors from scaffolds and style prompts via parametric roofs, LLM prompt refinement, material retrieval, and geometry-aware assembly while preserving structural constraints.
In: Proceedings of the IEEE/CVF Con- ference on Computer Vision and Pattern Recognition (CVPR)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
InFlux++ introduces a synthetic training dataset and an extended real-world benchmark for per-frame camera intrinsics estimation, showing that finetuning on synthetic data improves focal length prediction.
citing papers explorer
-
ShellMaker: Language-Guided Exterior Completion under Structural Constraints
ShellMaker generates complete building exteriors from scaffolds and style prompts via parametric roofs, LLM prompt refinement, material retrieval, and geometry-aware assembly while preserving structural constraints.
-
InFlux++: Real and Synthetic Data for Estimating Dynamic Camera Intrinsics
InFlux++ introduces a synthetic training dataset and an extended real-world benchmark for per-frame camera intrinsics estimation, showing that finetuning on synthetic data improves focal length prediction.