Title | ||
---|---|---|
IRS - A Large Naturalistic Indoor Robotics Stereo Dataset to Train Deep Models for Disparity and Surface Normal Estimation. |
Abstract | ||
---|---|---|
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. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/ICME51207.2021.9428423 | ICME |
Keywords | DocType | Citations |
Stereopsis,Rendering (computer graphics),Monocular vision,Ground truth,Computer vision,Deep learning,Robotics,Lens flare,RGB color model,Computer science,Artificial intelligence | Conference | 0 |
PageRank | References | Authors |
0.34 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Qiang Wang | 1 | 33 | 18.67 |
Zheng Shizhen | 2 | 0 | 0.68 |
Qingsong Yan | 3 | 0 | 0.34 |
Fei Deng | 4 | 0 | 3.04 |
Kaiyong Zhao | 5 | 325 | 20.30 |
Xiaowen Chu | 6 | 1273 | 101.81 |