A two-view network to predict depth and ego motion from monocular sequences

Researchers from the Embedded Systems and Robotics group at TCS Research & Innovation have recently developed a two-view depth network to infer depth and ego-motion from consecutive monocular sequences. Their approach, presented in a paper pre-published on arXiv, also incorporates epipolar constraints, which enhance the network's geometric understanding.

from News on Artificial Intelligence and Machine Learning http://bit.ly/2TPVWme
SHARE
    Blogger Comment
    Facebook Comment

0 comments:

Post a Comment