ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses

no code implementations • 30 Oct 2024 • Junjie Ni, Guofeng Zhang, Guanglin Li, Yijin Li, Xinyang Liu, Zhaoyang Huang, Hujun Bao

On the YFCC100M dataset, our matching accuracy is competitive with LoFTR, a state-of-the-art transformer-based architecture, while the inference speed is boosted to 4 times, even outperforming the CNN-based methods.

PATS: Patch Area Transportation with Subdivision for Local Feature Matching

no code implementations • CVPR 2023 • Junjie Ni, Yijin Li, Zhaoyang Huang, Hongsheng Li, Hujun Bao, Zhaopeng Cui, Guofeng Zhang

However, estimating scale differences between these patches is non-trivial since the scale differences are determined by both relative camera poses and scene structures, and thus spatially varying over image pairs.

Graph Matching Optical Flow Estimation +2