Combining optical-flow codes, LSTM temporal aggregation, and a GAN discriminator improves self-supervised monocular depth and pose estimation on KITTI and Cityscapes.
Driven to Distraction: Self-Supervised Distractor Learning for Robust Monocular Visual Odometry in Urban Environments
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Sequential Adversarial Learning for Self-Supervised Deep Visual Odometry
Combining optical-flow codes, LSTM temporal aggregation, and a GAN discriminator improves self-supervised monocular depth and pose estimation on KITTI and Cityscapes.