Part aware method improves 3D CAD reconstruction from noisy scans
CADonatello: Towards Real-World Multi-Part 3D CAD Reconstruction
Computer Vision and Pattern Recognition
Summary
Reconstructing detailed 3D CAD models from real-world scans is challenging because objects often have many connected parts, and scan data can be noisy. The authors present a new approach called CADonatello that breaks down scanned objects into parts before rebuilding each part separately. They also created a dataset that helps the system learn to interpret noisy scan sections better. Tests show this approach works well on complex real objects and noisy scans, improving over previous methods.
What this means in practice
- •For manufacturing engineers: Rebuild precise CAD models of multi-part products directly from noisy 3D scans to speed up reverse engineering workflows.
- •For industrial designers: Generate editable parametric CAD parts from real-world scanned prototypes to enable easier modifications and iterations.
Authors
Ahmet Serdar Karadeniz, Dimitrios Mallis, Parsa Akbari Chianeh, Kseniya Cherenkova, Anis Kacem, Djamila Aouada
Abstract
Existing methods for CAD reconstruction from 3D scans achieve strong performance on standard benchmarks, yet their effectiveness often degrades in real-world scenarios where objects consist of multiple parts and scan artifacts such as noise. A key reason is that current CAD reconstruction datasets predominantly contain single-part models and clean geometric inputs, limiting the ability of learned models to generalize to realistic settings. In this work, we introduce CADonatello, a part-aware framework for reconstructing parametric CAD models from real-world 3D scans. Our approach first decomposes the input geometry into structurally meaningful components using a foundation-scale 3D part segmentation model, and then reconstructs each component independently through a cross-section-driven pipeline that performs sketch parameterization followed by an extrusion. To improve the robustness of sketch parameterization to scan-derived cross-sections, we further introduce CC3D Cross-Sections, a dataset of paired rasterized cross-section images from realistic scans and their corresponding parametric sketches derived from aligned CAD models. This dataset enables effective domain adaptation from clean CAD sketch images to scan-derived cross-section images. Extensive experiments demonstrate that the proposed approach improves generalization to noisy scans and enables reliable reconstruction of complex multi-part objects across multiple real-world CAD reverse engineering benchmarks.