Supervised Learning of the Next-Best-View for 3D Object Reconstruction

Abstract

Motivated by the advances in 3D sensing technology and the spreading of low-cost robotic platforms, 3D object reconstruction has become a common task in many areas. Nevertheless, the selection of the optimal sensor pose that maximizes the reconstructed surface is a problem that remains open. It is known in the literature as the next-best-view planning problem. In this paper, we propose a novel next-best-view planning scheme based on supervised deep learning. The scheme contains an algorithm for automatic generation of datasets and an original three-dimensional convolutional neural network (3D-CNN) used to learn the next-best-view. Unlike previous work where the problem is addressed as a search, the trained 3D-CNN directly predicts the sensor pose. We present a comparison of the proposed network against a similar net, and we present several experiments of the reconstruction of unknown objects validating the effectiveness of the proposed scheme.

Under review in Pattern Recognition Letters

References in corpus (2)

• Adam: A Method for Stochastic Optimization
• Learn-to-Score: Efficient 3D Scene Exploration by Predicting View Utility

Cited by in corpus (6)

• Next-best-view Regression using a 3D Convolutional Neural Network
• Attention-driven Next-best-view Planning for Efficient Reconstruction of Plants and Targeted Plant Parts
• The Surface Edge Explorer (SEE): A measurement-direct approach to next best view planning
• Active 3D Shape Reconstruction from Vision and Touch
• Next-Best-View Estimation based on Deep Reinforcement Learning for Active Object Classification
• Deep SIMBAD: Active Landmark-based Self-localization Using Ranking -based Scene Descriptor