# C3VDReg: A Benchmark for Local-to-Local Colonoscopic Registration toward Anatomical Localization

arXiv: https://arxiv.org/abs/2511.00260 · HTML: https://mlsanity.com/paper/2511.00260/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 31 Oct 2025.

## Builds on (most cited first, 11 of 11)

- [Deep Closest Point: Learning Representations for Point Cloud Registration](https://mlsanity.com/paper/1905.03304/) (2019)
- [PointNetLK: Robust & Efficient Point Cloud Registration using PointNet](https://mlsanity.com/paper/1903.05711/) (2019)
- [Geometric Transformer for Fast and Robust Point Cloud Registration](https://mlsanity.com/paper/2202.06688/) (2022)
- [Deep Learning in Medical Image Registration: A Survey](https://mlsanity.com/paper/1903.02026/) (2019)
- [REGTR: End-to-end Point Cloud Correspondences with Transformers](https://mlsanity.com/paper/2203.14517/) (2022)
- [A comprehensive survey on point cloud registration](https://mlsanity.com/paper/2103.02690/) (2021)
- [Colonoscopy 3D Video Dataset with Paired Depth from 2D-3D Registration](https://mlsanity.com/paper/2206.08903/) (2022)
- [REAL-Colon: A dataset for developing real-world AI applications in colonoscopy](https://mlsanity.com/paper/2403.02163/) (2024)
- [SimCol3D -- 3D Reconstruction during Colonoscopy Challenge](https://mlsanity.com/paper/2307.11261/) (2023)
- [Motion-based Camera Localization System in Colonoscopy Videos](https://mlsanity.com/paper/2012.01690/) (2020)
- [SegCol Challenge: Semantic Segmentation for Tools and Fold Edges in Colonoscopy data](https://mlsanity.com/paper/2412.16078/) (2024)

## Abstract (arXiv)

Anatomy-aware colonoscopic navigation requires localizing partial endoscopic observations on a stable 3D reference to support coverage assessment, revisited-region awareness, and CT-guided navigation. However, rigid point cloud registration in the colon differs fundamentally from standard benchmarks: surfaces are locally homogeneous, haustral folds are repetitive, views are highly partial, and reconstructed depth is noisy. We present C3VDReg, a dataset and benchmark derived from the Colonoscopy 3D Video Dataset (C3VD). For each frame, C3VDReg generates source point clouds via depth reprojection and target point clouds by raycasting CT meshes from matched camera poses. The benchmark comprises 10,015 viewpoint-matched partial-to-partial point cloud pairs (including 2,088 held-out test pairs) and evaluates baseline models under a standardized protocol: 8,192 points per cloud, source-only perturbations, fixed pose conventions, and unified metrics. Crucially, C3VDReg enables a systematic investigation of failure modes. We find that high geometric overlap alone is insufficient for reliable pose recovery: despite 74.3-93.1% ground-truth overlap, registration recall remains low across all evaluated methods. Through overlap, pose error, and translation decomposition analyses, we identify translation ambiguity along repetitive tubular anatomy as the primary bottleneck. This challenges the common assumption that increasing overlap or correspondence quality guarantees accurate registration, highlighting the need for stronger anatomical and contextual constraints. Code, model checkpoints, and data are available at https://github.com/linzhe001/C3VDReg .