2 papers
cs.CV2026
REDI-Match: Rotation-Equivariant Distillation for Efficient and Robust Dense Matching
Yinji Ge, Guixu Zheng, Wulong Guo +5
Vision Foundation Models (VFMs) have significantly advanced dense feature matching, yet severe in-plane rotation remains a critical challenge. Existing solutions face a fundamental…
cs.CV2022
RRL:Regional Rotation Layer in Convolutional Neural Networks
Zongbo Hao, Tao Zhang, Mingwang Chen +1
Convolutional Neural Networks (CNNs) perform very well in image classification and object detection in recent years, but even the most advanced models have limited rotation invaria…