基于轻量级专家混合与本征图像对齐的内窥镜可泛化深度估计增强方法
Boosting Generalizable Depth Estimation in Endoscopy by Mixture of Lightweight Experts and Intrinsic Image Alignment
浏览论文内容
中文总结 AI 辅助
本文提出自监督框架EndoMINI，结合低秩专家混合与本征图像对齐，在多内窥镜数据集上实现了更优的可泛化深度估计性能。
中文摘要 AI 辅助
深度估计是内窥镜手术中三维感知的重要任务，但不同内窥镜场景中的光照干扰和特征多样性仍是可泛化深度估计与自身运动估计的挑战。为此，本文提出一种用于内窥镜场景深度估计的新型自监督框架EndoMINI。具体而言，提出低秩专家混合（MiLoRE）以实现参数高效微调，同时提升模型对不同特性场景的适应性；此外，引入本征图像对齐（IIA）至训练损失，通过新型本征图像分解网络缓解内窥镜中的光反射影响。在SCARED数据集（监督深度估计）、Hamlyn与SERV-CT两个内窥镜数据集（零样本深度估计）上开展评估，与现有先进方法对比，实验结果表明所提模型性能优异，且验证了核心贡献的有效性。
英文摘要
Depth estimation is a significant task for 3D perception in endoscopic surgeries. However, illumination interference and feature diversity in various endoscopic scenes are still challenges for generalizable depth estimation and ego-motion estimation. Based on this, a novel self-supervised framework, EndoMINI, is proposed for depth estimation in endoscopic scenes. Specifically, mixture of low-rank experts (MiLoRE) is proposed to perform parameter-efficient fine-tuning, which can also boost the model adaptation to scenes with different characteristics. Meanwhile, an intrinsic image alignment (IIA) is introduced into the training loss to alleviate the influence of light reflectance in endoscopy with a novel intrinsic image decomposition network. The proposed method is evaluated on SCARED datasets for supervised depth estimation, and two endoscopic datasets, Hamlyn and SERV-CT, for zero-shot depth estimation, compared with state-of-the-art works as well. The experimental results demonstrate outstanding performance of the proposed model and the effects of the main contributions.
发表机构
- The Chinese University of Hong Kong（香港中文大学）
- Shenzhen Loop Area Institute（深圳河套学院）
机构由 AI 辅助整理，请以论文原文为准。
