BCLNet：用于双视图对应关系修剪的双边共识学习
BCLNet: Bilateral Consensus Learning for Two-View Correspondence Pruning
AI总结：
提出BCLNet网络，通过并行上下文学习策略同时捕获局部和全局共识以获取双边共识，并设计重新校准块增强鲁棒性，在双视图对应关系修剪任务中显著提升了相机位姿估计精度与训练速度。
摘要：
对应关系修剪旨在两幅相关图像之间建立可靠的对应关系并恢复相对相机运动。现有方法通常采用渐进式策略来处理局部和全局上下文，重点强调从局部到全局的过渡，导致忽略了不同上下文之间的交互。为了解决这个问题，我们提出了一种并行上下文学习策略，为双视图对应关系修剪任务获取双边共识。在我们的方法中，我们设计了一个独特的自注意力块来捕获全局上下文，并与已建立的局部上下文学习模块并行处理，使我们能够同时捕获局部和全局共识。通过结合这些局部和全局共识，我们得到了所需的双边共识。我们还设计了一个重新校准块，减少错误共识信息的影响并增强模型的鲁棒性。我们努力的成果是双边共识学习网络（BCLNet），它能够高效估计相机位姿并识别内点（真实对应关系）。大量实验结果表明，我们的网络不仅在基准数据集上超越了最先进的方法，而且展示了跨各种特征提取技术的强大泛化能力。值得注意的是，BCLNet在未知室外数据集上比次优方法获得了3.98%的mAP5°提升，并明显加快了模型训练速度。源代码将发布于：https://github.com/guobaoxiao/BCLNet。
英文摘要：
Correspondence pruning aims to establish reliable correspondences between two related images and recover relative camera motion. Existing approaches often employ a progressive strategy to handle the local and global contexts, with a prominent emphasis on transitioning from local to global, resulting in the neglect of interactions between different contexts. To tackle this issue, we propose a parallel context learning strategy that involves acquiring bilateral consensus for the two-view correspondence pruning task. In our approach, we design a distinctive self-attention block to capture global context and parallel process it with the established local context learning module, which enables us to simultaneously capture both local and global consensuses. By combining these local and global consensuses, we derive the required bilateral consensus. We also design a recalibration block, reducing the influence of erroneous consensus information and enhancing the robustness of the model. The culmination of our efforts is the Bilateral Consensus Learning Network (BCLNet), which efficiently estimates camera pose and identifies inliers (true correspondences). Extensive experiments results demonstrate that our network not only surpasses state-of-the-art methods on benchmark datasets but also showcases robust generalization abilities across various feature extraction techniques. Noteworthily, BCLNet obtains 3.98\% mAP5$^{\circ}$ gains over the second best method on unknown outdoor dataset, and obviously accelerates model training speed. The source code will be available at: https://github.com/guobaoxiao/BCLNet.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
