NSL-SLAM: High-Fidelity Neural Structured-Light Depth for Practical SLAM and Reconstruction

📄 arXiv: 2607.24495v1 📥 PDF

作者: Jiaheng Li, Binsheng Zhang, Xinhai Chang, Wenzheng Chen

分类: cs.CV

发布日期: 2026-07-27

备注: 13 pages, 9 figures


💡 一句话要点

提出NSL-SLAM以解决高保真结构光深度感知问题

🎯 匹配领域: 支柱三:空间感知与语义 (Perception & Semantics)

关键词: 结构光 深度感知 SLAM 神经网络 机器人导航 增强现实 虚拟现实

📋 核心要点

  1. 现有的结构光深度感知方法在深度质量和稳定性上存在不足,影响了SLAM系统的性能。
  2. NSL-SLAM通过结合单目深度先验与结构光解码,增强了深度感知的准确性,构建了以深度为中心的SLAM管道。
  3. 在Replica-SL基准测试中,NSL-SLAM实现了最佳跟踪精度,并在真实场景中表现出43.3%的轨迹偏差降低。

📝 摘要(中文)

结构光相机在众多设备中广泛应用于深度感知,近期的神经结构光解码方法显著提升了深度质量。SLAM系统可以从这种强大的深度感知中获益,可靠的几何信息能够实现稳定的跟踪和真实的重建。本文提出了NSL-SLAM,一个针对高保真结构光深度的实用SLAM系统。我们通过结合强大的单目深度先验,进一步增强了SL深度感知,并在Replica-SL上将深度RMSE降低了35%。实验结果表明,NSL-SLAM在合成Replica-SL基准上实现了最佳跟踪精度,并在真实场景中表现出色,展示了其在实际应用中的潜力。

🔬 方法详解

问题定义:本文旨在解决现有结构光深度感知方法在深度质量和稳定性上的不足,这些问题限制了SLAM系统的有效性和可靠性。

核心思路:NSL-SLAM的核心思想是通过结合强大的单目深度先验来增强结构光深度感知,从而提高SLAM系统的跟踪和重建性能。

技术框架:NSL-SLAM的整体架构包括深度感知模块和SLAM管道。深度感知模块利用改进的结构光解码技术,SLAM管道则以深度为主要跟踪信号,并结合稀疏视觉对应点进行轻量级的束调整。

关键创新:最重要的技术创新在于将单目深度先验与结构光解码相结合,显著降低了深度RMSE,并使得SLAM系统在跟踪和重建中表现出色。

关键设计:在参数设置上,采用了优化的损失函数和网络结构,以确保深度估计的准确性和SLAM系统的实时性。

🖼️ 关键图片

fig_0
fig_1
fig_2

📊 实验亮点

在实验中,NSL-SLAM在合成Replica-SL基准上实现了最佳跟踪精度,并在共享深度协议下,重建F-score提高了1.6分。此外,在8个真实场景的基准测试中,NSL-SLAM在所有序列中避免了灾难性失败,轨迹偏差比选定基线降低了43.3%。

🎯 应用场景

NSL-SLAM的研究成果在机器人导航、增强现实和虚拟现实等领域具有广泛的应用潜力。通过提供高保真的深度信息,该系统能够在复杂环境中实现更为精准的定位与地图构建,提升用户体验和系统的实用性。

📄 摘要(原文)

Structured-light (SL) cameras power depth sensing in millions of devices, and recent neural SL decoding methods have substantially improved their depth quality. SLAM systems can benefit greatly from such strong depth sensing, where reliable geometry enables stable tracking and faithful reconstruction. In this work, we present NSL-SLAM, a practical SLAM system tailored for high-fidelity structured-light depth. We first strengthen SL depth sensing: inspired by the neural structured-light (NSL) method, we further incorporate strong monocular depth priors into the SL stereo decoding, reducing depth RMSE by 35% on Replica-SL compared to NSL. We then build a depth-centric SLAM pipeline with this stronger depth: because structured-light geometry is dense and metrically accurate, we keep it as the primary tracking signal, and add only sparse visual correspondences for geometrically degenerate cases and lightweight bundle adjustment for long-range drift. Our depth estimator and SLAM design reinforce each other: stronger depth makes a simple SLAM pipeline effective, and the depth-centric pipeline ensures this advantage transfers to downstream reconstruction. Experimentally, on the synthetic Replica-SL benchmark, NSL-SLAM achieves the best tracking accuracy and improves reconstruction F-score by 1.6 points over the SOTA baseline under a shared-depth protocol. On a real benchmark of 8 challenging scenes, it is the only method that avoids catastrophic failure on all sequences while achieving 43.3% lower trajectory deviation than selected baselines. The SLAM system runs online at 20.9 FPS, demonstrating that stronger structured-light depth and depth-centric system design together enable practical, robust SLAM.