A Petrovai, S Nedevschi - … of the IEEE/CVF conference on …, 2022 - openaccess.thecvf.com
We present a novel self-distillation based self-supervised monocular depth estimation (SD- SSMDE) learning framework. In the first step, our network is trained in a self-supervised …
M Rey-Area, M Yuan… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Abstract 360deg cameras can capture complete environments in a single shot, which makes 360deg imagery alluring in many computer vision tasks. However, monocular depth …
TW Hui - Proceedings of the IEEE/CVF conference on …, 2022 - openaccess.thecvf.com
Unsupervised methods have showed promising results on monocular depth estimation. However, the training data must be captured in scenes without moving objects. To push the …
S Shao, Z Pei, W Chen, W Zhu, X Wu, D Sun… - Medical image …, 2022 - Elsevier
Recently, self-supervised learning technology has been applied to calculate depth and ego- motion from monocular videos, achieving remarkable performance in autonomous driving …
M He, L Hui, Y Bian, J Ren, J Xie, J Yang - European Conference on …, 2022 - Springer
Existing self-supervised monocular depth estimation methods can get rid of expensive annotations and achieve promising results. However, these methods suffer from severe …
Z Liu, S Wu, S Jin, S Ji, Q Liu, S Lu… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
Predicting human motion from historical pose sequence is crucial for a machine to succeed in intelligent interactions with humans. One aspect that has been obviated so far, is the fact …
Conventional self-supervised monocular depth prediction methods are based on a static environment assumption, which leads to accuracy degradation in dynamic scenes due to the …
K Zhou, L Hong, C Chen, H Xu, C Ye, Q Hu… - European Conference on …, 2022 - Springer
Self-supervised depth learning from monocular images normally relies on the 2D pixel-wise photometric relation between temporally adjacent image frames. However, they neither fully …
Self-supervised monocular depth estimation enables robots to learn 3D perception from raw video streams. This scalable approach leverages projective geometry and ego-motion to …