无需重训练，用注意力机制精准修正关键点位置。
XRefine: Attention-Guided Keypoint Match Refinement
- 基于交叉注意力，仅用关键点周围图像块实现亚像素级精修。
- 在MegaDepth等数据集上提升几何估计精度，优于现有方法。
- 通用性强，可跨检测器使用，也适用于多视角特征追踪。
稀疏关键点匹配对3D视觉任务至关重要，但现有关键点检测器常产生空间误差。传统精修方法依赖匹配关键点位置对齐，但通常针对特定检测器，需重新训练。我们提出XRefine，一种无需依赖检测器内部表示的检测器无关型亚像素关键点精修方法，仅利用关键点中心的图像块进行预测。其基于交叉注意力的架构可学习精修坐标，实现跨检测器泛化。此外，XRefine可扩展至处理多视角特征轨迹。在MegaDepth、KITTI和ScanNet上的实验表明，该方法持续提升几何估计精度，性能优于现有精修方法，同时保持高效推理速度。代码与训练模型见https://github.com/boschresearch/xrefine。
原文摘要 · Abstract (English)
Sparse keypoint matching is crucial for 3D vision tasks, yet current keypoint detectors often produce spatially inaccurate matches. Existing refinement methods mitigate this issue through alignment of matched keypoint locations, but they are typically detector-specific, requiring retraining for each keypoint detector. We introduce XRefine, a novel, detector-agnostic approach for sub-pixel keypoint refinement that operates solely on image patches centered at matched keypoints. Our cross-attention-based architecture learns to predict refined keypoint coordinates without relying on internal detector representations, enabling generalization across detectors. Furthermore, XRefine can be extended to handle multi-view feature tracks. Experiments on MegaDepth, KITTI, and ScanNet demonstrate that the approach consistently improves geometric estimation accuracy, achieving superior performance compared to existing refinement methods while maintaining runtime efficiency. Our code and trained models can be found at https://github.com/boschresearch/xrefine.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。