VirtualWorlds as Proxy for Multi-object Tracking Analysis
Citations Over TimeTop 1% of 2016 papers
Abstract
Modern computer vision algorithms typically require expensive data acquisition and accurate manual labeling. In this work, we instead leverage the recent progress in computer graphics to generate fully labeled, dynamic, and photo-realistic proxy virtual worlds. We propose an efficient real-to-virtual world cloning method, and validate our approach by building and publicly releasing a new video dataset, called "Virtual KITTI", automatically labeled with accurate ground truth for object detection, tracking, scene and instance segmentation, depth, and optical flow. We provide quantitative experimental evidence suggesting that (i) modern deep learning algorithms pre-trained on real data behave similarly in real and virtual worlds, and (ii) pre-training on virtual data improves performance. As the gap between real and virtual worlds is small, virtual worlds enable measuring the impact of various weather and imaging conditions on recognition performance, all other things being equal. We show these factors may affect drastically otherwise high-performing deep models for tracking.
Related Papers
- → 3D Virtual worlds and the metaverse(2013)1,057 cited
- → Metaverse for education – Virtual or real?(2023)33 cited
- → The Future of Metaverse in the Virtual Era and Physical World: Analysis and Applications(2023)7 cited
- → The Digital Big Bang in the Metaverse Era(2022)7 cited
- → Pedagogical Potential of Virtual Worlds(2017)