# C3VD-DEFCOL: A Deformable Colonoscopy Dataset with Time-Resolved 3D Ground Truth and Realistic Appearance

arXiv: https://arxiv.org/abs/2606.07891 · HTML: https://mlsanity.com/paper/2606.07891/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 27 of its 41 references that are in the map.
- First posted on arXiv 5 Jun 2026.

## Builds on (most cited first, 27 of 27)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [LTX-2: Efficient Joint Audio-Visual Foundation Model](https://mlsanity.com/paper/2601.03233/) (2026)
- [In-Context LoRA for Diffusion Transformers](https://mlsanity.com/paper/2410.23775/) (2024)
- [Dense Extreme Inception Network: Towards a Robust CNN Model for Edge Detection](https://mlsanity.com/paper/1909.01955/) (2019)
- [Colonoscopy 3D Video Dataset with Paired Depth from 2D-3D Registration](https://mlsanity.com/paper/2206.08903/) (2022)
- [EndoMapper dataset of complete calibrated endoscopy procedures](https://mlsanity.com/paper/2204.14240/) (2022)
- [On the Content Bias in Fr'echet Video Distance](https://mlsanity.com/paper/2404.12391/) (2024)
- [EndoGSLAM: Real-Time Dense Reconstruction and Tracking in Endoscopic Surgeries using Gaussian Splatting](https://mlsanity.com/paper/2403.15124/) (2024)
- [SAGE: SLAM with Appearance and Geometry Prior for Endoscopy](https://mlsanity.com/paper/2202.09487/) (2022)
- [A deep learning framework for quality assessment and restoration in video endoscopy](https://mlsanity.com/paper/1904.07073/) (2019)
- [VR-Caps: A Virtual Environment for Capsule Endoscopy](https://mlsanity.com/paper/2008.12949/) (2020)
- [SD-DefSLAM: Semi-Direct Monocular SLAM for Deformable and Intracorporeal Scenes](https://mlsanity.com/paper/2010.09409/) (2020)
- [SimCol3D -- 3D Reconstruction during Colonoscopy Challenge](https://mlsanity.com/paper/2307.11261/) (2023)
- [Gaussian Pancakes: Geometrically-Regularized 3D Gaussian Splatting for Realistic Endoscopic Reconstruction](https://mlsanity.com/paper/2404.06128/) (2024)
- [C3VDv2 -- Colonoscopy 3D video dataset with enhanced realism](https://mlsanity.com/paper/2506.24074/) (2025)
- [GAN Inversion for Data Augmentation to Improve Colonoscopy Lesion Classification](https://mlsanity.com/paper/2205.02840/) (2022)
- [The Drunkard's Odometry: Estimating Camera Motion in Deforming Scenes](https://mlsanity.com/paper/2306.16917/) (2023)
- [Improving colonoscopy lesion classification using semi-supervised deep learning](https://mlsanity.com/paper/2009.03162/) (2020)
- [ColonCrafter: A Depth Estimation Model for Colonoscopy Videos Using Diffusion Priors](https://mlsanity.com/paper/2509.13525/) (2025)
- [ColonSplat: Reconstruction of Peristaltic Motion in Colonoscopy with Dynamic Gaussian Splatting](https://mlsanity.com/paper/2603.06860/) (2026)

## Abstract (arXiv)

3D reconstruction could improve colonoscopy by estimating mucosal coverage and alerting clinicians to missed regions during screening. However, algorithm development is limited as no current datasets provide both a realistic in vivo appearance and dense, time-resolved 3D ground truth, especially under non-rigid deformation. We present C3VD-DEFCOL, a framework and dataset for evaluating deformable colonoscopy reconstruction with paired geometry and realistic texture. Starting from C3VD/C3VDv2 colon meshes and camera trajectories, we generate controlled deformations of the colon surface, including peristaltic waves and centerline motion, and render per-frame depth, surface normals, optical flow, camera poses, and time-stamped 3D meshes. We then use the rendered geometry, primarily depth, to condition an LTX-2.3-based sim-to-real translation model that produces RGB clips with in vivo-like mucosal color, texture, vasculature, and specular appearance while preserving the underlying 3D scene structure. The resulting dataset contains 110 videos from 11 unique colon mesh geometries, with varying camera trajectories, appearances, and parameterized deformation regimes, including three peristaltic severity levels that serve as controlled evaluation axes. We evaluate the generated videos using appearance realism, geometric consistency, and temporal consistency metrics, and use the paired ground truth to benchmark the downstream task of pose estimation in deformable 3D reconstruction. Our experiments show how pose estimation error increases with increasing deformation severity, providing a controlled stress test that is not possible with existing in vivo datasets. Overall, C3VD-DEFCOL is designed as a reproducible, quantitative evaluation platform for testing deformable 3D reconstruction algorithms, with the goal of reducing the domain gap between synthetic datasets and in vivo colonoscopy.