用于单目内窥镜中多帧深度估计的可学习Patchmatch与自教学方法
Learnable Patchmatch and Self-Teaching for Multi-Frame Depth Estimation in Monocular Endoscopy
AI总结：
针对内窥镜无监督单目深度估计中时间相关性利用受限问题，提出集成可学习Patchmatch模块与交叉/自教学一致性的多帧模型，提升低纹理、亮度波动场景性能，在多数据集上超越SOTA。
摘要：
本研究深入探讨内窥镜中的无监督单目深度估计问题，该问题在训练阶段利用相邻帧建立监督信号。对于许多临床应用（如手术导航），测试时也可获取时间相关帧。由于缺乏深度线索，在训练和测试阶段充分利用多视频帧间的时间相关性对准确深度估计至关重要。然而，内窥镜场景中的若干挑战（如低且同质化的纹理、帧间亮度波动）限制了时间相关性带来的性能提升。为充分利用这一相关性，我们提出一种新型无监督多帧单目深度估计模型。该模型集成可学习的Patchmatch模块，以自适应增强低同质化纹理区域的判别能力，并通过交叉教学和自教学一致性为亮度波动提供有效正则化。此外，作为自教学范式的副产品，当测试时输入更多帧时，该模型能提升深度预测性能。我们在SCARED、EndoSLAM、Hamlyn和SERV-CT等多个数据集上进行了详细实验，结果表明我们的模型优于当前最先进的竞争对手。源代码和训练模型将在论文被接受后公开。
英文摘要：
This work delves into unsupervised monocular depth estimation in endoscopy, which leverages adjacent frames to establish a supervisory signal during the training phase. For many clinical applications, e.g., surgical navigation, temporally correlated frames are also available at test time. Due to the lack of depth clues, making full use of the temporal correlation among multiple video frames at both phases is crucial for accurate depth estimation. However, several challenges in endoscopic scenes, such as low and homogeneous textures and inter-frame brightness fluctuations, limit the performance gain from the temporal correlation. To fully exploit it, we propose a novel unsupervised multi-frame monocular depth estimation model. The proposed model integrates a learnable patchmatch module to adaptively increase the discriminative ability in regions with low and homogeneous textures, and enforces cross-teaching and self-teaching consistencies to provide efficacious regularizations towards brightness fluctuations. Furthermore, as a byproduct of the self-teaching paradigm, the proposed model is able to improve the depth predictions when more frames are input at test time. We conduct detailed experiments on multiple datasets, including SCARED, EndoSLAM, Hamlyn and SERV-CT. The experimental results indicate that our model exceeds the state-of-the-art competitors. The source code and trained models will be publicly available upon the acceptance.
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。
