CLIDD: 跨层独立可变形描述用于高效且判别性的局部特征表示
CLIDD: Cross-Layer Independent Deformable Description for Efficient and Discriminative Local Feature Representation
AI总结：
CLIDD通过跨层独立可变形描述实现高效且判别性的局部特征表示，提供高精度匹配与低计算开销的解决方案。
摘要：
鲁棒的局部特征表示对于空间智能任务如机器人导航和增强现实至关重要。建立可靠的对应关系需要提供高判别力和计算效率的描述符。为此，我们引入了跨层独立可变形描述（CLIDD），一种通过直接从独立特征层次采样来实现卓越区别的方法。该方法利用可学习的偏移量来捕捉多尺度下的细粒度结构细节，同时避免了统一密集表示的计算负担。为了确保实时性能，我们实现了硬件感知的内核融合策略，以最大化推理吞吐量。此外，我们开发了一个可扩展的框架，该框架集成了轻量级架构并与利用度量学习和知识蒸馏的训练协议相结合。该方案生成了一系列模型变体，以适应不同的部署约束。广泛的评估表明，我们的方法在匹配精度和计算效率方面均取得了优越的成果。具体而言，超紧凑的变体在仅使用0.004M参数的情况下，精度与SuperPoint相当，实现了模型大小的99.7%减少。此外，我们的高性能配置在边缘设备上超过了200 FPS，优于所有当前最先进的方法，包括高容量的DINOv2基框架。这些结果表明，CLIDD在最小的计算开销下实现了高精度的局部特征匹配，为实时空间智能任务提供了稳健且可扩展的解决方案。
英文摘要：
Robust local feature representations are essential for spatial intelligence tasks such as robot navigation and augmented reality. Establishing reliable correspondences requires descriptors that provide both high discriminative power and computational efficiency. To address this, we introduce Cross-Layer Independent Deformable Description (CLIDD), a method that achieves superior discriminability by sampling directly from independent feature hierarchies. This approach utilizes learnable offsets to capture fine-grained structural details across scales, without ever constructing a unified dense feature map, eliminating the memory and computation overhead of building a full-scale representation for a sparse sampling process. The per-keypoint per-layer offsets further break interpolation-induced correlation, preserving descriptor discriminability even at high keypoint densities. To ensure real-time performance, we implement a hardware-aware kernel fusion strategy that maximizes inference throughput. Furthermore, we develop a scalable framework that integrates lightweight architectures with a training protocol leveraging both metric learning and knowledge distillation. This scheme generates a wide spectrum of model variants optimized for diverse deployment constraints. Extensive evaluations demonstrate that our approach achieves superior matching accuracy and exceptional computational efficiency simultaneously. Furthermore, our high-performance configuration outperforms a broad range of current state-of-the-art methods while exceeding 200 FPS on edge devices. These results demonstrate that CLIDD delivers high-precision local feature matching with minimal computational overhead, providing a robust and scalable solution for real-time spatial intelligence tasks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
