@Article{cmes.2026.086568,
AUTHOR = {Legend Zhang, Junmin Lyu, Guan Yao, Wei Wei, Jiawei Tian, Bo Yang},
TITLE = {Stereo-Endoscopic Disparity Estimation via Pseudo-Label-Pretrained StyleGAN3 and Self-Supervised Test-Time Optimization},
JOURNAL = {Computer Modeling in Engineering \& Sciences},
VOLUME = {},
YEAR = {},
NUMBER = {},
PAGES = {{pages}},
URL = {http://www.techscience.com/CMES/online/detail/28157},
ISSN = {1526-1506},
ABSTRACT = {Accurate disparity estimation of soft tissue surfaces in endoscopic cardiac imaging is critical for minimally invasive surgical navigation and robotic surgery. Traditional geometric models, such as thin-plate splines, and recent learning-based stereo matching networks often struggle to balance nonlinear modeling capacity, computational cost, and robustness in dynamic surgical environments. We propose TTO-StyleGAN3 (Test-Time Optimization with a simplified StyleGAN3), a hybrid framework combining pseudo-label-supervised prior learning with self-supervised test-time latent optimization. A simplified StyleGAN3 generator is first pre-trained on pseudo-disparity maps generated by a teacher estimator and subsequently serves as a learned prior over plausible cardiac disparity fields. At inference, the generator is frozen, and the latent vector for each stereo pair is optimized without disparity supervision by minimizing photometric reconstruction, structural similarity, smoothness, and region-aware losses. This design avoids training a high-capacity end-to-end disparity predictor on manually annotated dense disparity datasets, although the compact generator prior is learned from teacher-generated pseudo-disparity maps. Experiments on a silicone heart phantom dataset and an <i>in vivo</i> dataset from Totally Endoscopic Coronary Artery Bypass (TECAB) procedures show that our method achieves competitive performance under the present pseudo-label and evaluation protocol, while reducing generator parameter count and the cost of training a full end-to-end disparity predictor.},
DOI = {10.32604/cmes.2026.086568}
}