CVLAB-Unibo/Real-time-self-adaptive-deep-stereo
A deep stereo network (MADNet) with modular adaptation for real-time unsupervised online domain adaptation to new environments.
Not currently ranked — collecting fresh signals.
star history
This repository implements MADNet (Modularly ADaptive Network), a lightweight deep stereo architecture for estimating disparity maps from stereo image pairs. The system performs unsupervised continuous online adaptation to maintain accuracy across different environments (e.g., real vs synthetic, indoor vs outdoor) without requiring labeled data. Modular ADaptation (MAD) enables training only sub-portions of the model, achieving real-time performance. Built with TensorFlow, the code accompanies both the CVPR 2019 oral paper and the follow-up TPAMI continual adaptation work.
Frequently asked
- What is CVLAB-Unibo/Real-time-self-adaptive-deep-stereo?
- A deep stereo network (MADNet) with modular adaptation for real-time unsupervised online domain adaptation to new environments.
- Is Real-time-self-adaptive-deep-stereo open source?
- Yes — CVLAB-Unibo/Real-time-self-adaptive-deep-stereo is open source, released under the Apache-2.0 license.
- What language is Real-time-self-adaptive-deep-stereo written in?
- CVLAB-Unibo/Real-time-self-adaptive-deep-stereo is primarily written in Python.
- How popular is Real-time-self-adaptive-deep-stereo?
- CVLAB-Unibo/Real-time-self-adaptive-deep-stereo has 422 stars on GitHub.
- Where can I find Real-time-self-adaptive-deep-stereo?
- CVLAB-Unibo/Real-time-self-adaptive-deep-stereo is on GitHub at https://github.com/CVLAB-Unibo/Real-time-self-adaptive-deep-stereo.