Depth-based reconstruction of three-dimensional (3D) shape of objects is one of core problems in computer vision with a lot of commercial applications. However, the 3D scanning for point cloud-based video streaming is expensive and is generally unattainable to an average user due to required setup of multiple depth sensors. We propose a novel hybrid modular artificial neural network (ANN) architecture, which can reconstruct smooth polygonal meshes from a single depth frame, using a priori knowledge. The architecture of neural network consists of separate nodes for recognition of object type and reconstruction thus allowing for easy retraining and extension for new object types. We performed recognition of nine real-world objects using the neural network trained on the ShapeNetCore model dataset. The results evaluated quantitatively using the Intersection-over-Union (IoU), Completeness, Correctness and Quality metrics, and qualitative evaluation by visual inspection demonstrate the robustness of the proposed architecture with respect to different viewing angles and illumination conditions.
Keywords: 3D depth scanning; 3D depth shape recognition; RGB-D sensors; hybrid neural networks.