Add model card for StereoAdapter
#1
by
nielsr
HF Staff
- opened
README.md
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
pipeline_tag: depth-estimation
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
# StereoAdapter: Adapting Stereo Depth Estimation to Underwater Scenes
|
| 6 |
+
|
| 7 |
+
This is the official repository for the paper:
|
| 8 |
+
[StereoAdapter: Adapting Stereo Depth Estimation to Underwater Scenes](https://huggingface.co/papers/2509.16415) (arXiv: [2509.16415](https://arxiv.org/abs/2509.16415))
|
| 9 |
+
|
| 10 |
+
**Project Website**: https://aigeeksgroup.github.io/StereoAdapter/
|
| 11 |
+
**Code**: https://github.com/AIGeeksGroup/StereoAdapter
|
| 12 |
+
**Dataset**: https://huggingface.co/datasets/AIGeeksGroup/UW-StereoDepth-40K
|
| 13 |
+
|
| 14 |
+
<img src="./assets/stereoadapter_logo.png" alt="logo" width="50"/>
|
| 15 |
+
|
| 16 |
+
## Abstract
|
| 17 |
+
Underwater stereo depth estimation provides accurate 3D geometry for robotics tasks such as navigation, inspection, and mapping, offering metric depth from low-cost passive cameras while avoiding the scale ambiguity of monocular methods. However, existing approaches face two critical challenges: (i) parameter-efficiently adapting large vision foundation encoders to the underwater domain without extensive labeled data, and (ii) tightly fusing globally coherent but scale-ambiguous monocular priors with locally metric yet photometrically fragile stereo correspondences. To address these challenges, we propose StereoAdapter, a parameter-efficient self-supervised framework that integrates a LoRA-adapted monocular foundation encoder with a recurrent stereo refinement module. We further introduce dynamic LoRA adaptation for efficient rank selection and pre-training on the synthetic UW-StereoDepth-40K dataset to enhance robustness under diverse underwater conditions. Comprehensive evaluations on both simulated and real-world benchmarks show improvements of 6.11% on TartanAir and 5.12% on SQUID compared to state-of-the-art methods, while real-world deployment with the BlueROV2 robot further demonstrates the consistent robustness of our approach.
|
| 18 |
+
|
| 19 |
+
## Citation
|
| 20 |
+
If you find our code or paper helpful, please consider starring ⭐ us and citing:
|
| 21 |
+
|
| 22 |
+
```bibtex
|
| 23 |
+
@article{wu2025stereoadapter,
|
| 24 |
+
title={StereoAdapter: Adapting Stereo Depth Estimation to Underwater Scenes},
|
| 25 |
+
author={Wu, Zhengri and Wang, Yiran and Wen, Yu and Zhang, Zeyu and Wu, Biao and Tang, Hao},
|
| 26 |
+
journal={arXiv preprint arXiv:2509.16415},
|
| 27 |
+
year={2025}
|
| 28 |
+
}
|
| 29 |
+
```
|