# Colon3R: Cross-Domain 3D Reconstruction from Monocular Colonoscopic Video

arXiv: https://arxiv.org/abs/2609.23961 · HTML: https://mlsanity.com/paper/2609.23961/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 21 Sep 2026.

## Builds on (most cited first, 14 of 14)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (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)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass](https://mlsanity.com/paper/2501.13928/) (2025)
- [MUSt3R: Multi-view Network for Stereo 3D Reconstruction](https://mlsanity.com/paper/2503.01661/) (2025)
- [Colonoscopy 3D Video Dataset with Paired Depth from 2D-3D Registration](https://mlsanity.com/paper/2206.08903/) (2022)
- [Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgery](https://mlsanity.com/paper/2401.06013/) (2024)
- [EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Camera](https://mlsanity.com/paper/2405.08672/) (2024)
- [SimCol3D -- 3D Reconstruction during Colonoscopy Challenge](https://mlsanity.com/paper/2307.11261/) (2023)
- [Endo3R: Unified Online Reconstruction from Dynamic Monocular Endoscopic Video](https://mlsanity.com/paper/2504.03198/) (2025)
- [NR-SLAM: Non-Rigid Monocular SLAM](https://mlsanity.com/paper/2308.04036/) (2023)
- [ColonAdapter: Geometry Estimation Through Foundation Model Adaptation for Colonoscopy](https://mlsanity.com/paper/2511.22250/) (2025)
- [Wat3R: Underwater 3D Geometry Learning without Annotations](https://mlsanity.com/paper/2607.08772/) (2026)

## Abstract (arXiv)

Monocular colonoscopic 3D reconstruction is important for surgical robotic colonoscopy, but remains challenging due to weak texture, specular reflections, limited view overlap, and non-rigid tissue motion. Conventional multi-view 3D reconstruction methods rely on stable correspondences and approximate rigidity, which are often violated in colonoscopy. Existing endoscopic methods often rely on domain-specific supervision, whereas there are not enough in-vivo labeled data available to adapt geometry foundation models to clinical colonoscopy. We present Colon3R, a cross-domain semi-supervised framework built on pretrained VGGT that transfers coupled camera, depth, and pointmap geometry from labeled phantom and simulated data to unlabeled in-vivo colonoscopy without requiring target-domain geometric annotations. Unlike source-only fine-tuning, which learns only from phantom and simulated data, Colon3R directly exploits unlabeled in-vivo video through teacher-derived cross-view supervision. Our proposed hierarchical quasi-rigid reliability selects reliable supervision at the sequence, directed-pair, and pixel levels, while source-preserving adaptation retains the learned coupled geometry during target-domain adaptation. Extensive experiments demonstrate that our method achieves superior overall performance over state-of-the-art approaches in depth, pointmap, and camera pose estimation. Qualitative comparisons on real in-vivo colonoscopy further show substantially more complete and geometrically consistent reconstructions than competing methods under clinical domain shift. The code is publicly available at https://github.com/vglx/Colon3R.