SC-Net: Improved Correspondence Learning with Context
Paper#Computer Vision, Deep Learning, Correspondence Learning🔬 Research|Analyzed: Jan 3, 2026 18:46•
Published: Dec 29, 2025 13:56
•1 min read
•ArXivAnalysis
This paper introduces SC-Net, a novel network for two-view correspondence learning. It addresses limitations of existing CNN-based methods by incorporating spatial and cross-channel context. The proposed modules (AFR, BFA, PAR) aim to improve position-awareness, robustness, and motion field refinement, leading to better performance in relative pose estimation and outlier removal. The availability of source code is a positive aspect.
Key Takeaways
- •Proposes SC-Net, a novel network for correspondence learning.
- •Integrates spatial and cross-channel context for improved performance.
- •Introduces AFR, BFA, and PAR modules for specific improvements.
- •Demonstrates state-of-the-art performance on benchmark datasets.
- •Source code is available for reproducibility.
Reference / Citation
View Original"SC-Net outperforms state-of-the-art methods in relative pose estimation and outlier removal tasks on YFCC100M and SUN3D datasets."