IRS (Indoor Robotics Stereo)
Introduced by Wang et al. in IRS: A Large Naturalistic Indoor Robotics Stereo Dataset to Train Deep Models for Disparity and Surface Normal Estimation
IRS is an open dataset for indoor robotics vision tasks, especially disparity and surface normal estimation. It contains totally 103,316 samples covering a wide range of indoor scenes, such as home, office, store and restaurant.
Source: https://github.com/HKBU-HPML/IRSPapers
| Paper | Code | Results | Date | Stars |
|---|
