SGANVO uses stacked GAN layers with recurrent connections to estimate depth and ego-motion unsupervisedly from images, reporting better or comparable results on the KITTI dataset.
”End-to-end, sequence-to-sequence probabilistic visual odometry through deep neural networks.” The International Journal of Robotics Research 37.4-5 (2018): 513-542
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
SGANVO: Unsupervised Deep Visual Odometry and Depth Estimation with Stacked Generative Adversarial Networks
SGANVO uses stacked GAN layers with recurrent connections to estimate depth and ego-motion unsupervisedly from images, reporting better or comparable results on the KITTI dataset.