B. Planche, Z. Wu, K. Ma, S. Sun, S. Kluckner, T. Chen, A. Hutter, S. Zakharov, H. Kosch, J. Ernst DepthSynth: Real-Time Realistic Synthetic Data Generation from CAD Models for 2.5D Recognition International Conference on 3D Vision (3DV), Qingdao, China, October 2017 (bib)
	Recent progress in computer vision has been dominated by deep neural networks trained over large amount of labeled data. Collecting such datasets is however a tedious, often impossible task; hence a surge in approaches relying solely on synthetic data for their training. For depth images however, discrepancies with real scans still noticeably affect the end performance. We thus propose an end-to-end framework which simulates the whole mechanism of these devices, generating realistic depth data from 3D models by comprehensively modeling vital factors e.g. sensor noise, material reflectance, surface geometry. Not only does our solution cover a wider range of sensors and achieve more realistic results than previous methods, assessed through extended evaluation, but we also go further by measuring the impact on the training of neural networks for various recognition tasks; demonstrating how our pipeline seamlessly integrates such architectures and consistently enhances their performance.
	This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each authors copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.