SC-Net: Robust Correspondence Learning via Spatial and Cross-Channel Context

Shuyuan Lin; Hailiang Liao; Qiang Qi; Junjie Huang; Taotao Lai; Jian Weng

AAAI 2026technical0 citations

SC-Net: Robust Correspondence Learning via Spatial and Cross-Channel Context

Shuyuan Lin, Hailiang Liao, Qiang Qi, Junjie Huang, Taotao Lai, Jian Weng

Abstract

Recent research has focused on using convolutional neural networks (CNNs) as the backbones in two-view correspondence learning, demonstrating significant superiority over methods based on multilayer perceptrons. However, CNN backbones that are not tailored to specific tasks may fail to effectively aggregate global context and oversmooth dense motion fields in scenes with large disparity. To address these problems, we propose a novel network named SC-Net, which effectively integrates bilateral context from both spatial and channel perspectives. Specifically, we design an adaptive focused regularization module (AFR) to enhance the model

BibTeX

@inproceedings{aaai2026_scnetrobustcorre,
  title = {SC-Net: Robust Correspondence Learning via Spatial and Cross-Channel Context},
  author = {Shuyuan Lin and Hailiang Liao and Qiang Qi and Junjie Huang and Taotao Lai and Jian Weng},
  booktitle = {AAAI 2026},
  year = {2026}
}