TY - JOUR N1 - This version is the author accepted manuscript. For information on re-use, please refer to the publisher?s terms and conditions. IS - 3 SP - 219 VL - 9 JF - Computer Methods in Biomechanics and Biomedical Engineering: Imaging and Visualization A1 - Brandao, P A1 - Psychogyios, D A1 - Mazomenos, E A1 - Stoyanov, D A1 - Janatka, M SN - 2168-1171 UR - https://dx.doi.org/10.1080/21681163.2020.1835561 TI - HAPNet: hierarchically aggregated pyramid network for real-time stereo matching EP - 224 AV - public Y1 - 2021/// KW - Convolutional neural networks KW - colonoscopy KW - computer-aided diagnosis ID - discovery10122492 N2 - Recovering the 3D shape of the surgical site is crucial for multiple computer-assisted interventions. Stereo endoscopes can be used to compute 3D depth but computational stereo is a challenging, non-convex and inherently discontinuous optimisation problem. In this paper, we propose a deep learning architecture which avoids the explicit construction of a cost volume of similarity which is one of the most computationally costly blocks of stereo algorithms. This makes training our network significantly more efficient and avoids the needs for large memory allocation. Our method performs well, especially around regions comprising multiple discontinuities around surgical instrumentation or around complex small structures and instruments. The method compares well to the state-of-the-art techniques while taking a different methodological angle to computational stereo problem in surgical video. ER -