Xianqi Wang, Hao Yang, Hangtian Wang, Junda Cheng, Gangwei Xu, Min Lin, Xin Yang
Huazhong University of Science and Technology, Optics Valley Laboratory
- 04/01/2026: Update the evaluation code.
conda create -n promptstereo python=3.12
conda activate promptstereo
pip install tqdm numpy wandb opt_einsum hydra-core
pip install imageio scipy torch torchvision opencv-python matplotlib
pip install xformers accelerate scikit-image
Data for evaluation:
| Model | Link |
|---|---|
| Depth-Anything-V2-Large | Download 🤗 |
| PromptStereo-Unlimited-192 | Download 🤗 |
accelerate launch evaluate_stereo.py
Default settings use bf16 precision with faster speed but a very little performance degration, you can set accelerator.mixed_precision to null to obtain entire performance.
Complete demo, training, and fine-tuning code will be released soon. More versions of models such as adapting to large disparity will also be released soon.
This project is based on Depth Anything V2, and MonSter. We thank the original authors for their excellent works.