CAOA -- Completion-Assisted Object-CAD Alignment

2026-06-16

AI Summary

This work addresses the challenge of aligning CAD models to real-world objects in indoor RGB-D scans under nine degrees of freedom—accounting for translation, rotation, and anisotropic scaling—amidst pervasive issues such as point cloud noise, missing geometry, and segmentation errors. To this end, the authors propose a unified alignment framework that integrates semantic context-aware point cloud completion with symmetry-aware pose estimation. A tailored synthetic data generation strategy is employed to mitigate the sim-to-real domain gap, while a symmetry-aware loss function enhances robustness for symmetric objects. The approach is evaluated on a newly introduced benchmark dataset, S2C-Completion, comprising over 8,500 annotated pairs, and achieves a 17% improvement in alignment accuracy over the current state-of-the-art on Scan2CAD.

Abstract

Accurately aligning CAD models to their corresponding objects in indoor RGB-D scans is a central challenge in 3D semantic reconstruction. The task requires estimating a 9-Degree-of-Freedom (DoF) pose-position, rotation, and scale along three axes-but is hindered by noisy and incomplete scans, as well as segmentation errors that cause geometric distortions. We present Completion-Assisted Object-CAD Alignment (CAOA), a method that integrates a semantically and contextually aware point cloud completion module with a symmetry-aware relative pose estimation algorithm, enabling precise alignment of CAD models to scanned objects. Existing completion methods are typically trained and evaluated on synthetic datasets, which often fail to generalize to real-world scans. To bridge this gap, we introduce a synthetic data generation strategy tailored to indoor scenes, significantly reducing the synthetic-to-real domain gap-validated through quantitative comparisons with widely used completion datasets. In addition, we release S2C-Completion, an expert-annotated dataset of over 8,500 object-CAD pairs from Scan2CAD, created for real-world indoor single-object completion and intended as a new benchmark for this task. For object-CAD alignment, we incorporate symmetry information via a symmetry-aware loss, improving robustness to symmetric ambiguities. On the Scan2CAD benchmark, CAOA achieves a 17% accuracy improvement over state-of-the-art methods.

Problem

• CAD alignment
• RGB-D scans
• 3D semantic reconstruction
• point cloud completion
• object pose estimation

Innovation

• point cloud completion
• CAD alignment
• symmetry-aware pose estimation
• synthetic-to-real domain gap
• Scan2CAD benchmark