Improving Semantic Segmentation through Spatio-Temporal Consistency Learned from Videos

Pasad Ankita
Pasad Ankita
Gordon Ariel
Gordon Ariel
Cited by: 0|Views68

Abstract:

We leverage unsupervised learning of depth, egomotion, and camera intrinsics to improve the performance of single-image semantic segmentation, by enforcing 3D-geometric and temporal consistency of segmentation masks across video frames. The predicted depth, egomotion, and camera intrinsics are used to provide an additional supervision s...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments