Camera augmentation: enabling uncalibrated stereo matching of MIS images by training from the wealth of public synthetic image datasets
Existing models for stereo matching in Minimally-Invasive Surgery (MIS) require calibrated stereo images. Accurate calibration is however often unavailable intraoperatively. Training an uncalibrated stereo model is thus attractive but challenging owing to the lack of disparity-labelled surgical images. We leverage the wealth of non-medical stereo synthetic image datasets. These data were however generated in ideal conditions --rectified and with centred principal points-- hence differ from real uncalibrated MIS images. We propose camera augmentation, a new type of image augmentation that augments a dataset by altering the camera’s orientation and intrinsic parameters via geometric parameters. We augment the idealised existing datasets, sampling the geometric augmentation parameters from distributions estimated through an in-depth analysis and modelling of stereo laparoscopes. This forms the Camera Augmentation Training Strategy (CATS), with which we retrain RAFTStereo and IGEV++ for zero-shot uncalibrated stereo matching in MIS.
Representative sample from StereoMIS (P2_7)
Representative sample from SCARED (D1K3)
Usage policy
If you use the CATS models in your research, please cite the associated publication. The models are freely available for research purposes only and are not licensed for commercial use.
BibTeX
@article{sharifian2026camera,
title={Camera augmentation: enabling uncalibrated stereo matching of minimally invasive surgery images by training from the wealth of public synthetic image datasets},
author={Sharifian, Rasoul and Rabbani, Navid and Zhang, Yongcong and Bartoli, Adrien},
journal={International Journal of Computer Assisted Radiology and Surgery},
pages={to apear},
year={2026},
publisher={Springer}
}