# ColonAdapter: Geometry Estimation Through Foundation Model Adaptation for Colonoscopy

arXiv: https://arxiv.org/abs/2511.22250 · HTML: https://mlsanity.com/paper/2511.22250/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 33 references that are in the map.
- First posted on arXiv 27 Nov 2025.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [Vision Transformer Adapter for Dense Predictions](https://mlsanity.com/paper/2205.08534/) (2022)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth](https://mlsanity.com/paper/2104.14540/) (2021)
- [FoundationStereo: Zero-Shot Stereo Matching](https://mlsanity.com/paper/2501.09898/) (2025)
- [Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation](https://mlsanity.com/paper/2211.13202/) (2022)
- [Endo-Depth-and-Motion: Reconstruction and Tracking in Endoscopic Videos using Depth Networks and Photometric Constraints](https://mlsanity.com/paper/2103.16525/) (2021)
- [Colonoscopy 3D Video Dataset with Paired Depth from 2D-3D Registration](https://mlsanity.com/paper/2206.08903/) (2022)
- [Align3R: Aligned Monocular Depth Estimation for Dynamic Videos](https://mlsanity.com/paper/2412.03079/) (2024)
- [Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the Rescue](https://mlsanity.com/paper/2112.08122/) (2021)
- [EndoMapper dataset of complete calibrated endoscopy procedures](https://mlsanity.com/paper/2204.14240/) (2022)
- [EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Camera](https://mlsanity.com/paper/2405.08672/) (2024)
- [Bridging the Domain Gap in Satellite Pose Estimation: a Self-Training Approach based on Geometrical Constraints](https://mlsanity.com/paper/2212.12103/) (2022)
- [SimCol3D -- 3D Reconstruction during Colonoscopy Challenge](https://mlsanity.com/paper/2307.11261/) (2023)
- [LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models](https://mlsanity.com/paper/2412.07746/) (2024)
- [Endo3R: Unified Online Reconstruction from Dynamic Monocular Endoscopic Video](https://mlsanity.com/paper/2504.03198/) (2025)
- [MonoPCC: Photometric-invariant Cycle Constraint for Monocular Depth Estimation of Endoscopic Images](https://mlsanity.com/paper/2404.16571/) (2024)
- [DARES: Depth Anything in Robotic Endoscopic Surgery with Self-supervised Vector-LoRA of the Foundation Model](https://mlsanity.com/paper/2408.17433/) (2024)
- [Mono3R: Exploiting Monocular Cues for Geometric 3D Reconstruction](https://mlsanity.com/paper/2504.13419/) (2025)

## Built on by (most cited first, 2 of 2)

- [CoGE: Sim-to-Real Online Geometric Estimation for Monocular Colonoscopy](https://mlsanity.com/paper/2605.13038/) (2026)
- [Colon3R: Cross-Domain 3D Reconstruction from Monocular Colonoscopic Video](https://mlsanity.com/paper/2609.23961/) (2026)

## Abstract (arXiv)

Estimating 3D geometry from monocular colonoscopy images is challenging due to non-Lambertian surfaces, moving light sources, and large textureless regions. While recent 3D geometric foundation models eliminate the need for multi-stage pipelines, their performance deteriorates in clinical scenes. These models are primarily trained on natural scene datasets and struggle with specularity and homogeneous textures typical in colonoscopy, leading to inaccurate geometry estimation. In this paper, we present ColonAdapter, a self-supervised fine-tuning framework that adapts geometric foundation models for colonoscopy geometry estimation. Our method leverages pretrained geometric priors while tailoring them to clinical data. To improve performance in low-texture regions and ensure scale consistency, we introduce a Detail Restoration Module (DRM) and a geometry consistency loss. Furthermore, a confidence-weighted photometric loss enhances training stability in clinical environments. Experiments on both synthetic and real datasets demonstrate that our approach achieves state-of-the-art performance in camera pose estimation, monocular depth prediction, and dense 3D point map reconstruction, without requiring ground-truth intrinsic parameters.