Beyond Foundation Models: Distilling Geometric Priors for Lightweight Monocular Depth Estimation in Endoscopy
- 5 May 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. PP (02780062) , 1
Abstract
In recent times, geometric foundation models have demonstrated remarkable performance in depth estimation tasks, benefiting from exposure to large-scale data that enables the learning of intricate geometric structures and spatial dependencies. However, their large parameter sizes and high computational complexity pose significant challenges in meeting the efficiency requirements of downstream surgical applications. Consequently, the design of a high-performance yet lightweight monocular depth estimator has become a focal point of research. To this end, we harness the rich geometric priors encoded in geometric foundation models and introduce a novel trinity distillation scheme that transfers geometric knowledge across three complementary dimensions, namely spatial, spectral and gradient, into a compact depth estimator. To further enhance prediction quality, we develop a semantic distribution alignment strategy to effectively suppress pseudo-texture artifacts arising from the limited semantic representation capability of the lightweight estimator. Extensive experiments on the SCARED, SERV-CT, Hamlyn, and C3VD datasets demonstrate that the proposed method either surpasses or achieves comparable performance to previous state-of-the-art competitors, with a smaller model size and reduced computational overhead. Code will be available at: https://github.com/ShuweiShao/LiteNet.Keywords
Funding Information
- National Natural Science Foundation of China (62303450)
- National Natural Science Foundation of China (U20A20195)
- National Key Research and Development Program of China (2023YFB4705700)
This publication has 55 references indexed in Scilit:
- Endo-FASt3r: Endoscopic Foundation Model Adaptation for Structure from Motion2025
- DARES: Depth Anything in Robotic Endoscopic Surgery with Self-supervised Vector-LoRA of the Foundation Model2025
- EndoDepth: A Benchmark for Assessing Robustness in Endoscopic Depth Prediction2024
- EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Camera2024
- Meta-learning of feature distribution alignment for enhanced feature sharingKnowledge-Based Systems, 2024
- Spatial-Frequency Domain Information Integration for Pan-Sharpening2022
- Unsupervised Scale-Consistent Depth Learning from VideoInternational Journal of Computer Vision, 2021
- The Challenge of Augmented Reality in Surgery2020
- Real-Time Stereo Reconstruction in Robotically Assisted Minimally Invasive Surgery2010
- Dynamic Guidance for Robotic Surgery Using Image-Constrained Biomechanical Models2010