Scholarlink

<p>Sparse local feature matching techniques have made significant strides in a variety of visual geometry tasks. Among them, the weakly supervised methods have drawn particular attention recently and outperform the fully supervised counterparts via decoupled describe-then-detect training. However, they often rely on policy gradients for detector training, overlooking keypoint reliability. Meanwhile, many of the sparse local feature matching methods put more emphasis on accuracy over speed, making them unfriendly for real-time applications. To address these issues, we introduce the differentiable keypoint extraction and the dispersity peak loss to generate clean score maps and enhance the reliability of the keypoints. The proposed model is trained under the weakly supervised fashion by leveraging the epipolar constraint between images. Additionally, we propose an efficient model that achieves a good balance between accuracy and speed. Experiments on various public benchmarks show our method achieving higher performance than existing ones. Code will be available at <a href="https://github.com/FYL0123/WSDK">https://github.com/FYL0123/WSDK</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Epipolar constraint-guided differentiable keypoint detection and description

  • 期刊论文

  • 发表日期：

    2025年2月9日

查看全文
  • Xi Li,
  • Yulong Feng,
  • Xianguo Yu,
  • Yirui Cong,
  • Lili Chen

摘要

Sparse local feature matching techniques have made significant strides in a variety of visual geometry tasks. Among them, the weakly supervised methods have drawn particular attention recently and outperform the fully supervised counterparts via decoupled describe-then-detect training. However, they often rely on policy gradients for detector training, overlooking keypoint reliability. Meanwhile, many of the sparse local feature matching methods put more emphasis on accuracy over speed, making them unfriendly for real-time applications. To address these issues, we introduce the differentiable keypoint extraction and the dispersity peak loss to generate clean score maps and enhance the reliability of the keypoints. The proposed model is trained under the weakly supervised fashion by leveraging the epipolar constraint between images. Additionally, we propose an efficient model that achieves a good balance between accuracy and speed. Experiments on various public benchmarks show our method achieving higher performance than existing ones. Code will be available at https://github.com/FYL0123/WSDK.