基于状态空间建模与稀疏相关的可扩展特征匹配
Scalable Feature Matching via State Space Modeling and Sparse Correlation
用 Conv-Mamba 混合骨干网络以线性复杂度替代 Transformer 的长程建模，并用免训练范数过滤把全相关矩阵稀疏化，可直接迁移到任何需要高分辨率稠密/半稠密匹配的视觉流程（如光流、立体匹配、SLAM 前端）以降低显存与延迟。
原文依据 a hybrid Conv-Mamba backbone for efficient cross-scale and cross-view feature extraction with linear complexity
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论高效且鲁棒的特征匹配对延迟敏感和资源受限的应用至关重要。然而，当前许多半稠密特征匹配方法的计算量随空间分辨率呈二次增长，其原因要么是基于 Transformer 的长程上下文建模，要么是冗余的全相关计算。为克服这些局限，我们提出 SLiM（Salient Lightweight Matching），一种新颖的可扩展特征匹配方法，能够在低显存占用和低延迟下给出可靠的匹配，尤其在高分辨率下表现突出。我们的方法引入三项关键创新：(1) 一种混合 Conv-Mamba 骨干网络，以线性复杂度实现高效的跨尺度与跨视角特征提取；(2) 一种免训练的基于范数的特征过滤机制，实现稀疏相关，从而在推理阶段显著降低计算开销；(3) 一种轻量级循环坐标精化，在亚像素精度上超越基于期望的回归。实验结果表明，SLiM 在室内与室外基准上均稳定取得较强的精度—效率权衡，在显存占用、推理速度和高分辨率可扩展性方面具有明显优势。这些结果证明了 SLiM 的实际效率与强可扩展性。项目主页：https://github.com/Band-127/SLiM
英文原文摘要 1335 字符
Efficient and robust feature matching is crucial for latency-sensitive and resource-constrained applications. However, many current semi-dense feature matching methods scale quadratically with spatial resolution, either due to transformer-based long-range context modeling or from redundant full correlation computations. To overcome these limitations, we present SLiM (Salient Lightweight Matching), a novel scalable feature matching method that delivers reliable matches with low memory footprint and latency, especially at high resolutions. Our approach introduces three key innovations: (1) a hybrid Conv-Mamba backbone for efficient cross-scale and cross-view feature extraction with linear complexity, (2) a training-free norm-based feature filtering mechanism, enabling sparse correlation that significantly reduces computation overhead during inference, and (3) a lightweight recurrent coordinate refinement that surpasses expectation-based regression in subpixel accuracy. Experimental results show that SLiM consistently achieves a strong accuracy-efficiency trade-off across indoor and outdoor benchmarks, with clear advantages in memory usage, inference speed, and high-resolution scalability. These results demonstrate the practical efficiency and strong scalability of SLiM. Project page: https://github.com/Band-127/SLiM