A search-classify approach for cluttered indoor scene understanding

Abstract

Figure 1: A raw scan of a highly cluttered indoor scene is given (left). Applying our search-classify method, we segment the scene into meaningful objects (middle: chairs (blue) and tables (purple)), followed by a template deform-to-fit reconstruction (right). AbstractWe present an algorithm for recognition and reconstruction of scanned 3D indoor scenes. 3D indoor reconstruction is particularly challenging due to object interferences, occlusions and overlapping which yield incomplete yet very complex scene arrangements. Since it is hard to assemble scanned segments into complete models, traditional methods for object recognition and reconstruction would be inefficient. We present a search-classify approach which interleaves segmentation and classification in an iterative manner. Using a robust classifier we traverse the scene and gradually propagate classification information. We reinforce classification by a template fitting step which yields a scene reconstruction. We deform-to-fit templates to classified objects to resolve classification ambiguities. The resulting reconstruction is an approximation which captures the general scene arrangement. Our results demonstrate successful classification and reconstruction of cluttered indoor scenes, captured in just few minutes.

Online Structure Analysis for Real-Time Indoor Scene Reconstruction

“…Thus, object-level structure analysis is investigated to match the captured objects to the high-quality 3D models in databases for improved reconstruction quality [Nan et al 2012;Shao et al 2012;Salas-Moreno et al 2013], while object repetition is explored to speed up large scale indoor scene reconstruction [Kim et al 2012;Mattausch et al 2014]. In contrast, our approach does not rely on a 3D model database, but performs online repeated object analysis to simultaneously reduce the scanning burden by providing real-time guidance to the user and improve the reconstruction quality through local volume fusion.…”

Learning Hierarchical Semantic Segmentations of LIDAR Data

“…Shen et al [25] use a database of segmented models and assembly-based modeling algorithms to reconstruct novel 3D models. Nan et al [20] integrate a region growing segmentation algorithm with object recognition for cluttered indoor scene understanding. Most work with 3D CAD models has been demonstrated on only a few small scenes for objects with small shape variations (e.g., chairs).…”

Creating Product Models From Point Cloud of Civil Structures Based on Geometric Similarity

“…The resulting recall ratios for surfaces and pillars were about 80%, and about 60% for all other parts. Nan et al (2012) proposed a method for decomposing cluttered indoor point cloud data into furniture by replacing polygons with the most similar types in the database. In this method, the input point cloud was first roughly decomposed into level or curved surfaces.…”