Search Results for author:
Found 3 papers, 1 papers with code
S³Net: Semantic-Aware Self-supervised Depth Estimation with Monocular Videos and Synthetic Data
In order to learn such a scalable depth estimation model, we require a ton of data and labels which are targeted towards specific use-cases.
$S^3$Net: Semantic-Aware Self-supervised Depth Estimation with Monocular Videos and Synthetic Data
We present $S^3$Net, a self-supervised framework which combines these complementary features: we use synthetic and real-world images for training while exploiting geometric, temporal, as well as semantic constraints.
SIGNet: Semantic Instance Aided Unsupervised 3D Geometry Perception
SIGNet is shown to improve upon the state-of-the-art unsupervised learning for depth prediction by 30% (in squared relative error).
Ranked #62 on
Monocular Depth Estimation
on KITTI Eigen split
