Automatically Annotating Indoor Images with CAD Models via RGB-D Scans
This provides a solution for researchers and practitioners in computer vision to generate ground truth 3D annotations without manual effort, though it is incremental as it builds on existing datasets and methods.
The paper tackles the problem of automatically annotating indoor images with CAD models using RGB-D scans, achieving annotations as accurate as manual ones through expert evaluation.
We present an automatic method for annotating images of indoor scenes with the CAD models of the objects by relying on RGB-D scans. Through a visual evaluation by 3D experts, we show that our method retrieves annotations that are at least as accurate as manual annotations, and can thus be used as ground truth without the burden of manually annotating 3D data. We do this using an analysis-by-synthesis approach, which compares renderings of the CAD models with the captured scene. We introduce a 'cloning procedure' that identifies objects that have the same geometry, to annotate these objects with the same CAD models. This allows us to obtain complete annotations for the ScanNet dataset and the recent ARKitScenes dataset.