JiawangBian/sc_depth_pl
Self-supervised monocular depth estimation system using deep learning to predict depth from single camera video.
Not currently ranked — collecting fresh signals.
star history
SC-Depth provides three versions (V1, V2, V3) of self-supervised learning approaches for monocular depth estimation from video sequences. Version 1 introduced geometry consistency loss and self-discovered masks for scale-consistent predictions. Version 2 added an auto-rectify network (ARN) to handle large rotational motions in hand-held camera footage. Version 3 improved robustness for highly dynamic scenes and sharper depth at object boundaries using external pretrained depth networks.
Frequently asked
- What is JiawangBian/sc_depth_pl?
- Self-supervised monocular depth estimation system using deep learning to predict depth from single camera video.
- Is sc_depth_pl open source?
- Yes — JiawangBian/sc_depth_pl is open source, released under the GPL-3.0 license.
- What language is sc_depth_pl written in?
- JiawangBian/sc_depth_pl is primarily written in Python.
- How popular is sc_depth_pl?
- JiawangBian/sc_depth_pl has 487 stars on GitHub.
- Where can I find sc_depth_pl?
- JiawangBian/sc_depth_pl is on GitHub at https://github.com/JiawangBian/sc_depth_pl.