Sheikh Zeinoddin, M;
Lena, C;
Qu, J;
Carlini, L;
Magro, M;
Kim, S;
De Momi, E;
... Islam, M; + view all
(2025)
DARES: Depth Anything in Robotic Endoscopic Surgery with Self-supervised Vector-LoRA of the Foundation Model.
In: Bue, Alessio Del and Canton, Cristian and Pont-Tuset, Jordi and Tommasi, Tatiana, (eds.)
Computer Vision – ECCV 2024 Workshops. ECCV 2024. Lecture Notes in Computer Science, vol 15633.
Springer, Cham
![[thumbnail of Hoque_DARES_MedICSS2024.pdf]](https://discovery.ucl.ac.uk/style/images/fileicons/text.png) |
Text
Hoque_DARES_MedICSS2024.pdf - Accepted Version Access restricted to UCL open access staff until 13 May 2026. Download (1MB) |
Abstract
Robotic-assisted surgery (RAS) relies on accurate depth estimation for 3D reconstruction and visualization. While foundation models like Depth Anything Models (DAM) show promise, directly applying them to surgery often yields suboptimal results. Fully fine-tuning on limited surgical data can cause overfitting and catastrophic forgetting, compromising model robustness and generalization. Although Low-Rank Adaptation (LoRA) addresses some adaptation issues, its uniform parameter distribution neglects the inherent feature hierarchy, where earlier layers, learning more general features, require more parameters than later ones. To tackle this issue, we introduce Depth Anything in Robotic Endoscopic Surgery (DARES), a novel approach that employs a new adaptation technique, Vector Low-Rank Adaptation (Vector-LoRA) on the DAM V2 to perform self-supervised monocular depth estimation in RAS scenes. To enhance learning efficiency, we introduce Vector-LoRA by integrating more parameters in earlier layers and gradually decreasing parameters in later layers. We also design a reprojection loss based on the multi-scale SSIM error to enhance depth perception by better tailoring the foundation model to the specific requirements of the surgical environment. The proposed method is validated on the SCARED dataset and demonstrates superior performance over recent state-of-the-art self-supervised monocular depth estimation techniques, achieving an improvement of 13.3% in the absolute relative error metric. The code and pre-trained weights are available at https://github.com/mobarakol/DARES.
| Type: | Proceedings paper |
|---|---|
| Title: | DARES: Depth Anything in Robotic Endoscopic Surgery with Self-supervised Vector-LoRA of the Foundation Model |
| Event: | Computer Vision – ECCV 2024 Workshops (ECCV 2024) |
| ISBN-13: | 9783031919787 |
| DOI: | 10.1007/978-3-031-91979-4_1 |
| Publisher version: | https://doi.org/10.1007/978-3-031-91979-4_1 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Med Phys and Biomedical Eng |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10211121 |
Archive Staff Only
 |
View Item |
