Virtual Worlds as Proxy for Multi-Object Tracking Analysis
This provides a cost-effective proxy for analyzing multi-object tracking algorithms, though it is incremental as it builds on existing computer graphics and deep learning methods.
The authors tackled the problem of expensive data acquisition and labeling for computer vision by creating Virtual KITTI, a photo-realistic virtual world dataset with automatic ground truth labeling for tasks like object tracking. They showed that pre-training on virtual data improves performance and that virtual worlds can measure the impact of weather and imaging conditions on tracking models.
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 (see http://www.xrce.xerox.com/Research-Development/Computer-Vision/Proxy-Virtual-Worlds), 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.