IRS: A Large Naturalistic Indoor Robotics Stereo Dataset to Train Deep Models for Disparity and Surface Normal Estimation
This addresses the problem of insufficient training data for indoor robotics scene understanding, though it is incremental as it builds on existing synthetic dataset methods.
The authors tackled the lack of high-quality ground truth for training deep models in indoor stereo vision by introducing the IRS dataset, a large-scale synthetic but naturalistic dataset with over 100K stereo images, and showed that it improves disparity estimation and enables DTN-Net to achieve state-of-the-art results for surface normal estimation.
Indoor robotics localization, navigation, and interaction heavily rely on scene understanding and reconstruction. Compared to the monocular vision which usually does not explicitly introduce any geometrical constraint, stereo vision-based schemes are more promising and robust to produce accurate geometrical information, such as surface normal and depth/disparity. Besides, deep learning models trained with large-scale datasets have shown their superior performance in many stereo vision tasks. However, existing stereo datasets rarely contain the high-quality surface normal and disparity ground truth, which hardly satisfies the demand of training a prospective deep model for indoor scenes. To this end, we introduce a large-scale synthetic but naturalistic indoor robotics stereo (IRS) dataset with over 100K stereo RGB images and high-quality surface normal and disparity maps. Leveraging the advanced rendering techniques of our customized rendering engine, the dataset is considerably close to the real-world captured images and covers several visual effects, such as brightness changes, light reflection/transmission, lens flare, vivid shadow, etc. We compare the data distribution of IRS with existing stereo datasets to illustrate the typical visual attributes of indoor scenes. Besides, we present DTN-Net, a two-stage deep model for surface normal estimation. Extensive experiments show the advantages and effectiveness of IRS in training deep models for disparity estimation, and DTN-Net provides state-of-the-art results for normal estimation compared to existing methods.