Advancing Depth Anything Model for Unsupervised Monocular Depth Estimation in Endoscopy
This work addresses depth estimation for minimally invasive endoscopic surgery, enhancing surgeons' spatial awareness to improve precision and safety, but it is incremental as it builds on existing models.
The paper tackled the problem of unsupervised monocular depth estimation in endoscopic images by fine-tuning the Depth Anything Model with a low-rank adaptation and residual block, achieving state-of-the-art performance on the SCARED and Hamlyn datasets while minimizing trainable parameters.
Depth estimation is a cornerstone of 3D reconstruction and plays a vital role in minimally invasive endoscopic surgeries. However, most current depth estimation networks rely on traditional convolutional neural networks, which are limited in their ability to capture global information. Foundation models offer a promising approach to enhance depth estimation, but those models currently available are primarily trained on natural images, leading to suboptimal performance when applied to endoscopic images. In this work, we introduce a novel fine-tuning strategy for the Depth Anything Model and integrate it with an intrinsic-based unsupervised monocular depth estimation framework. Our approach includes a low-rank adaptation technique based on random vectors, which improves the model's adaptability to different scales. Additionally, we propose a residual block built on depthwise separable convolution to compensate for the transformer's limited ability to capture local features. Our experimental results on the SCARED dataset and Hamlyn dataset show that our method achieves state-of-the-art performance while minimizing the number of trainable parameters. Applying this method in minimally invasive endoscopic surgery can enhance surgeons' spatial awareness, thereby improving the precision and safety of the procedures.