DepthSynth: Real-Time Realistic Synthetic Data Generation from CAD Models for 2.5D Recognition
This addresses the tedious data collection issue in computer vision by providing a realistic synthetic alternative for depth-based recognition, though it is incremental as it builds on existing synthetic data methods.
The paper tackles the problem of generating realistic synthetic depth data from CAD models to train neural networks for 2.5D recognition, achieving more realistic results and enhancing network performance consistently across tasks.
Recent progress in computer vision has been dominated by deep neural networks trained over large amounts 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 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.