SOURCE-LINKED INTELLIGENCE

RealCAD: Towards Real-World Image-to-CAD Reconstruction under Domain Shift and Parameter Bias

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

Reconstructing editable Computer-Aided Design (CAD) models from images is essential for downstream modification, manufacturing, and design reuse. However, existing image-to-CAD methods are developed predominantly on synthetic renderings and face two coupled obstacles: a substantial appearance domain gap between synthetic and real images, and a previously overlooked parameter bias in widely used CAD data. We show that the local normalization adopted by DeepCAD concentrates several geometric parameters around a few discrete values while encoding substantial information in a single scale factor.

Read original source ↗ Open in workspace

recordType

paper

region

Global