Model
NVOF is a deep learning based optical flow estimation and stereo matching solution.
Use the NGC CLI to download:
Copied!
| Field | Response |
|---|---|
| Participation considerations from adversely impacted groups (protected classes) in model design and testing: | Race, Age, Gender, Skin Color |
| Measures taken to mitigate against unwanted bias: | Our model is designed to estimate the motion between pairs of input images. Therefore, the data used is synthetic data, which includes virtual images of various indoor and outdoor scenes. Our data doesn't require explicit content related to people or religion and so on. To mitigate against unwanted bias, during the process of generation and collection of our data, the richness and diversity of scenes have been taken into account through the adjustment of relevant parameters. |