.png){kind=icon}
.png){kind=icon}
Return
CPFormer-Net: Correspondence Pruning Transformer With Structured Context Aggregation
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2025.3636997.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Finding reliable correspondences between two-view images remains challenging, particularly under high outlier ratios. While existing transformer-based methods excel in capturing global context, they often fail to maintain robust long-range semantic dependencies across input correspondences. To address this, we propose a novel correspondence pruning transformer network, called CPFormer-Net, which enhances long-range dependency modeling via structured context aggregation for accurate correspondence pruning. Specifically, we propose the CPFormer module, which integrates global context with local geometric cues to ensure both structural coherence and semantic consistency. Then, we propose the Semantic Graph Network (SEGN) module with a dual-branch architecture to improve representation. One branch applies Structured Context Aggregation (SCA) block with an agent attention mechanism to explicitly model long-range dependencies, enabling it to filter channels, recalibrate features, and guide attention, while the other branch employs pooling and normalization to preserve spatial relations. Extensive experiments on indoor and outdoor benchmarks demonstrate that CPFormer-Net consistently outperforms state-of-the-art methods in inlier identification and correspondence matching.
Keywords:
Correspondence pruning
long-range dependency modeling
structured context aggregation
Journal
I
IF:
3.9
Papers:
610
Citations:
0