mlsanityData to 14 Oct 2026

EndoGMDE: Generalizable Monocular Depth Estimation with Mixture of Low-Rank Experts for Diverse Endoscopic Scenes

arXiv 2509.01206 ↗First posted 1 Sep 2025cs.CV cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Self-supervised monocular depth estimation is a significant task for low-cost and efficient 3D scene perception and measurement in endoscopy. However, the variety of illumination conditions and scene features is still the primary challenges for depth estimation in endoscopic scenes. In this work, a novel self-supervised framework is proposed for monocular depth estimation in diverse endoscopy. Firstly, considering the diverse features in endoscopic scenes with different tissues, a novel block-wise mixture of dynamic low-rank experts is proposed to efficiently finetune the foundation model for endoscopic depth estimation. In the proposed module, based on the input feature, different experts with a small amount of trainable parameters are adaptively selected for weighted inference, from low-rank experts which are allocated based on the generalization of each block. Moreover, a novel self-supervised training framework is proposed to jointly cope with brightness inconsistency and reflectance interference. The proposed method outperforms state-of-the-art works on SCARED dataset and SimCol dataset. Furthermore, the proposed network also achieves the best generalization based on zero-shot depth estimation on C3VD, Hamlyn and SERV-CT dataset. The outstanding performance of our model is further demonstrated with 3D reconstruction and ego-motion estimation. The proposed method could contribute to accurate endoscopy for minimally invasive measurement and surgery. The evaluation codes will be released upon acceptance, while the demo videos can be found on: https://endo-gmde.netlify.app/.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 51 references that are in the map. First posted on arXiv 1 Sep 2025.

Builds on

27 of 51 references.

References · 27

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  3. 2024Depth Anything V2cited by 1,422
  4. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  5. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 782
  6. 2023AdaLoRA: Adaptive Budget Allocation for Parameter-Efficient Fine-Tuningcited by 357
  7. 2022MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformercited by 136
  8. 2024HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuningcited by 123
  9. 2021Stereo Correspondence and Reconstruction of Endoscopic Data Challengecited by 103
  10. 2022Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimationcited by 100
  11. 2021Endo-Depth-and-Motion: Reconstruction and Tracking in Endoscopic Videos using Depth Networks and Photometric Constraintscited by 81
  12. 2022Colonoscopy 3D Video Dataset with Paired Depth from 2D-3D Registrationcited by 80
15 more
  1. 2021Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the Rescuecited by 72
  2. 2019Unsupervised Learning for Intrinsic Image Decomposition from a Single Imagecited by 55
  3. 2022EndoMapper dataset of complete calibrated endoscopy procedurescited by 53
  4. 2024Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgerycited by 52
  5. 2024EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Cameracited by 43
  6. 2020SERV-CT: A disparity dataset from CT for validation of endoscopic 3D reconstructioncited by 23
  7. 2023Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Trainingcited by 20
  8. 2023SimCol3D -- 3D Reconstruction during Colonoscopy Challengecited by 19
  9. 2016Unified Depth Prediction and Intrinsic Image Decomposition from a Single Image via Joint Convolutional Neural Fieldscited by 17
  10. 2018Unsupervised Odometry and Depth Learning for Endoscopic Capsule Robotscited by 14
  11. 2024Leveraging Near-Field Lighting for Monocular Depth Estimation from Endoscopy Videoscited by 14
  12. 2024MonoPCC: Photometric-invariant Cycle Constraint for Monocular Depth Estimation of Endoscopic Imagescited by 10
  13. 2024DARES: Depth Anything in Robotic Endoscopic Surgery with Self-supervised Vector-LoRA of the Foundation Modelcited by 8
  14. 2023FS-Depth: Focal-and-Scale Depth Estimation from a Single Image in Unseen Indoor Scenecited by 7
  15. 2024WaterMono: Teacher-Guided Anomaly Masking and Enhancement Boosting for Robust Underwater Self-Supervised Monocular Depth Estimationcited by 4

Built on by

Not cited yet.