# C-DOG: Multi-View Multi-instance Feature Association Using Connected δ-Overlap Graphs

arXiv: https://arxiv.org/abs/2507.14095 · HTML: https://mlsanity.com/paper/2507.14095/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 59 references that are in the map.
- First posted on arXiv 18 Jul 2025.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views](https://mlsanity.com/paper/1901.04111/) (2019)
- [Direct Multi-view Multi-person 3D Pose Estimation](https://mlsanity.com/paper/2111.04076/) (2021)
- [ClusterGNN: Cluster-based Coarse-to-Fine Graph Neural Network for Efficient Feature Matching](https://mlsanity.com/paper/2204.11700/) (2022)
- [AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild](https://mlsanity.com/paper/2010.13302/) (2020)
- [Graph-Based 3D Multi-Person Pose Estimation Using Multi-View Images](https://mlsanity.com/paper/2109.05885/) (2021)
- [Towards Discriminative Representation: Multi-view Trajectory Contrastive Learning for Online Multi-object Tracking](https://mlsanity.com/paper/2203.14208/) (2022)
- [PPT: token-Pruned Pose Transformer for monocular and multi-view human pose estimation](https://mlsanity.com/paper/2209.08194/) (2022)
- [Lifting Multi-View Detection and Tracking to the Bird's Eye View](https://mlsanity.com/paper/2403.12573/) (2024)
- [Shape-aware Multi-Person Pose Estimation from Multi-View Images](https://mlsanity.com/paper/2110.02330/) (2021)
- [Adaptive Multi-view and Temporal Fusing Transformer for 3D Human Pose Estimation](https://mlsanity.com/paper/2110.05092/) (2021)
- [End2End Multi-View Feature Matching with Differentiable Pose Optimization](https://mlsanity.com/paper/2205.01694/) (2022)
- [Unpaired Multi-View Graph Clustering with Cross-View Structure Matching](https://mlsanity.com/paper/2307.03476/) (2023)
- [Near-Optimal Joint Object Matching via Convex Relaxation](https://mlsanity.com/paper/1402.1473/) (2014)
- [MessyTable: Instance Association in Multiple Camera Views](https://mlsanity.com/paper/2007.14878/) (2020)
- [Graph Neural Networks for Cross-Camera Data Association](https://mlsanity.com/paper/2201.06311/) (2022)
- [A General Multi-Graph Matching Approach via Graduated Consistency-regularized Boosting](https://mlsanity.com/paper/1502.05840/) (2015)
- [View-Centric Multi-Object Tracking with Homographic Matching in Moving UAV](https://mlsanity.com/paper/2403.10830/) (2024)
- [Fast, Accurate and Memory-Efficient Partial Permutation Synchronization](https://mlsanity.com/paper/2203.16505/) (2022)
- [CoMatcher: Multi-View Collaborative Feature Matching](https://mlsanity.com/paper/2504.01872/) (2025)
- [CLEAR: A Consistent Lifting, Embedding, and Alignment Rectification Algorithm for Multi-View Data Association](https://mlsanity.com/paper/1902.02256/) (2019)
- [Multi-person 3D pose estimation from unlabelled data](https://mlsanity.com/paper/2212.08731/) (2022)
- [EasyVis2: A Real Time Multi-view 3D Visualization System for Laparoscopic Surgery Training Enhanced by a Deep Neural Network YOLOv8-Pose](https://mlsanity.com/paper/2412.16742/) (2024)

## Abstract (arXiv)

Multi-view multi-instance feature association constitutes a crucial step in 3D reconstruction, facilitating the consistent grouping of object instances across various camera perspectives. The presence of multiple identical objects within a scene often leads to ambiguities for appearance-based feature matching algorithms. Our work circumvents this challenge by exclusively employing geometrical constraints, specifically epipolar geometry, for feature association. We introduce C-DOG (Connected delta-Overlap Graph), an algorithm designed for robust geometrical feature association, even in the presence of noisy feature detections. In a C-DOG graph, two nodes representing 2D feature points from distinct views are connected by an edge if they correspond to the same 3D point. Each edge is weighted by its epipolar distance. Ideally, true associations yield a zero distance; however, noisy feature detections can result in non-zero values. To robustly retain edges where the epipolar distance is less than a threshold delta, we employ a Szymkiewicz--Simpson coefficient. This process leads to a delta-neighbor-overlap clustering of 2D nodes. Furthermore, unreliable nodes are pruned from these clusters using an Inter-quartile Range (IQR)-based criterion. Our extensive experiments on synthetic benchmarks demonstrate that C-DOG not only outperforms geometry-based baseline algorithms but also remains remarkably robust under demanding conditions. This includes scenes with high object density, no visual features, and restricted camera overlap, positioning C-DOG as an excellent solution for scalable 3D reconstruction in practical applications.