# Bidirectional Semi-supervised Dual-branch CNN for Robust 3D Reconstruction of Stereo Endoscopic Images via Adaptive Cross and Parallel Supervisions arXiv: https://arxiv.org/abs/2210.08291 ยท HTML: https://mlsanity.com/paper/2210.08291/ ## Key facts - Cited by 6 papers in the map (data through 14 Oct 2026). - Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation. - Builds on 28 of its 46 references that are in the map. - First posted on arXiv 15 Oct 2022. ## Placed in - Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/) ## Builds on (most cited first, 28 of 28) - [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014) - [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015) - [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016) - [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019) - [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015) - [Unsupervised Monocular Depth Estimation with Left-Right Consistency](https://mlsanity.com/paper/1609.03677/) (2016) - [Pyramid Stereo Matching Network](https://mlsanity.com/paper/1803.08669/) (2018) - [End-to-End Learning of Geometry and Context for Deep Stereo Regression](https://mlsanity.com/paper/1703.04309/) (2017) - [End-to-End Semi-Supervised Object Detection with Soft Teacher](https://mlsanity.com/paper/2106.09018/) (2021) - [GA-Net: Guided Aggregation Net for End-to-end Stereo Matching](https://mlsanity.com/paper/1904.06587/) (2019) - [Group-wise Correlation Stereo Network](https://mlsanity.com/paper/1903.04025/) (2019) - [CFNet: Cascade and Fused Cost Volume for Robust Stereo Matching](https://mlsanity.com/paper/2104.04314/) (2021) - [Hierarchical Deep Stereo Matching on High-resolution Images](https://mlsanity.com/paper/1912.06704/) (2019) - [Stereo Correspondence and Reconstruction of Endoscopic Data Challenge](https://mlsanity.com/paper/2101.01133/) (2021) - [Learning monocular depth estimation infusing traditional stereo knowledge](https://mlsanity.com/paper/1904.04144/) (2019) - [Adaptive Unimodal Cost Volume Filtering for Deep Stereo Matching](https://mlsanity.com/paper/1909.03751/) (2019) - [Semi-Supervised Brain Lesion Segmentation with an Adapted Mean Teacher Model](https://mlsanity.com/paper/1903.01248/) (2019) - [Semi-supervised Skin Lesion Segmentation via Transformation Consistent Self-ensembling Model](https://mlsanity.com/paper/1808.03887/) (2018) - [Wasserstein Distances for Stereo Disparity Estimation](https://mlsanity.com/paper/2007.03085/) (2020) - [Self-Supervised Siamese Learning on Stereo Image Pairs for Depth Estimation in Robotic Surgery](https://mlsanity.com/paper/1705.08260/) (2017) - [Deep Learning and Conditional Random Fields-based Depth Estimation and Topographical Reconstruction from Conventional Endoscopy](https://mlsanity.com/paper/1710.11216/) (2017) - [Unsupervised Domain Adaptation for Depth Prediction from Images](https://mlsanity.com/paper/1909.03943/) (2019) - [SERV-CT: A disparity dataset from CT for validation of endoscopic 3D reconstruction](https://mlsanity.com/paper/2012.11779/) (2020) - [Self-Supervised Generative Adversarial Network for Depth Estimation in Laparoscopic Images](https://mlsanity.com/paper/2107.04644/) (2021) - [Rethinking Bayesian Deep Learning Methods for Semi-Supervised Volumetric Medical Image Segmentation](https://mlsanity.com/paper/2206.09293/) (2022) - [On the Importance of Stereo for Accurate Depth Estimation: An Efficient Semi-Supervised Deep Neural Network Approach](https://mlsanity.com/paper/1803.09719/) (2018) - [Semi-Supervised Adversarial Monocular Depth Estimation](https://mlsanity.com/paper/1908.02126/) (2019) - [Semi-Supervised Learning with Mutual Distillation for Monocular Depth Estimation](https://mlsanity.com/paper/2203.09737/) (2022) ## Built on by (most cited first, 6 of 6) - [IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching](https://mlsanity.com/paper/2409.00638/) (2024) - [MonoPCC: Photometric-invariant Cycle Constraint for Monocular Depth Estimation of Endoscopic Images](https://mlsanity.com/paper/2404.16571/) (2024) - [Unsupervised Stereo Matching Network For VHR Remote Sensing Images Based On Error Prediction](https://mlsanity.com/paper/2408.07419/) (2024) - [EndoLRMGS: Complete Endoscopic Scene Reconstruction combining Large Reconstruction Modelling and Gaussian Splatting](https://mlsanity.com/paper/2503.22437/) (2025) - [StereoMamba: Real-time and Robust Intraoperative Stereo Disparity Estimation via Long-range Spatial Dependencies](https://mlsanity.com/paper/2504.17401/) (2025) - [TiS-TSL: Image-Label Supervised Surgical Video Stereo Matching via Time-Switchable Teacher-Student Learning](https://mlsanity.com/paper/2511.06817/) (2025) ## Abstract (arXiv) Semi-supervised learning via teacher-student network can train a model effectively on a few labeled samples. It enables a student model to distill knowledge from the teacher's predictions of extra unlabeled data. However, such knowledge flow is typically unidirectional, having the performance vulnerable to the quality of teacher model. In this paper, we seek to robust 3D reconstruction of stereo endoscopic images by proposing a novel fashion of bidirectional learning between two learners, each of which can play both roles of teacher and student concurrently. Specifically, we introduce two self-supervisions, i.e., Adaptive Cross Supervision (ACS) and Adaptive Parallel Supervision (APS), to learn a dual-branch convolutional neural network. The two branches predict two different disparity probability distributions for the same position, and output their expectations as disparity values. The learned knowledge flows across branches along two directions: a cross direction (disparity guides distribution in ACS) and a parallel direction (disparity guides disparity in APS). Moreover, each branch also learns confidences to dynamically refine its provided supervisions. In ACS, the predicted disparity is softened into a unimodal distribution, and the lower the confidence, the smoother the distribution. In APS, the incorrect predictions are suppressed by lowering the weights of those with low confidence. With the adaptive bidirectional learning, the two branches enjoy well-tuned supervisions, and eventually converge on a consistent and more accurate disparity estimation. The extensive and comprehensive experimental results on four public datasets demonstrate our superior performance over other state-of-the-arts with a relative decrease of averaged disparity error by at least 9.76%.