AI Insight
This study presents CAOA, a method for accurately aligning CAD (Computer-Aided Design) models to real objects in 3D indoor scans by combining point cloud completion with symmetry-aware pose estimation. The researchers developed a new training approach to reduce the gap between synthetic and real-world data, and released S2C-Completion, a dataset of over 8,500 annotated object-CAD pairs for benchmarking. On the Scan2CAD benchmark, CAOA achieved 17% higher accuracy compared to existing state-of-the-art methods in estimating 9-degree-of-freedom pose parameters.
Why it matters
This advancement enables more accurate 3D semantic reconstruction of indoor environments, which has practical applications in augmented reality, robotics navigation, architectural design, and automated scene understanding. The released dataset and improved methods provide researchers with better tools for training and evaluating real-world 3D scene analysis systems.
Understand the Science
arXiv:2606.18429v2 Announce Type: replace-cross
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.