CHOW-SLAM：面向RGB-D SLAM的结合互补重叠窗口优化的紧凑混合表示方法
CHOW-SLAM: Compact Hybrid Representation with Complementary Overlap Window Optimization for RGB-D SLAM
浏览论文内容
中文总结 AI 辅助
本文提出CHOW-SLAM框架，通过紧凑P-H混合表示与互补重叠窗口策略构建空间、时间约束，结合ORB初始化与神经渲染优化，在多数据集上优于现有最优RGB-D SLAM方法。
中文摘要 AI 辅助
基于神经辐射场（NeRF）的同步定位与建图（SLAM）可实现稠密、连续的场景重建，但现有系统受限于有限的在线资源，难以同时构建两类约束：从场景表示中提取的紧凑且具有判别性的空间约束，以及从历史观测中得到的持久时间约束。为应对这一挑战，本文提出CHOW-SLAM，这是一种显式构建上述互补空间与时间约束的稠密RGB-D SLAM框架。空间层面，本文提出紧凑的参数化哈希（P-H）混合表示，该表示在P分支与H分支中按尺度以平面和网格组织组件，统一的多输出解码器进一步对齐由TSDF与密度诱导的射线终止分布，在紧凑参数预算下保留几何与外观信息。时间层面，本文提出互补重叠窗口策略，以避免优化被短期重叠或弱相关的历史观测主导；在固定预算内，该策略保留近期帧、选择高重叠局部帧，并引入时间分布的历史关键帧，损失感知关键帧插入与光束平差调度进一步使优化适配跟踪质量。此外，本文采用基于ORB的跟踪与几何位姿估计进行位姿初始化，随后通过神经渲染优化提升跟踪稳定性。在多个数据集上的广泛评估表明，CHOW-SLAM在场景重建质量与相机跟踪精度上均优于现有最优方法，源代码可在指定URL获取。
英文摘要
Simultaneous localization and mapping (SLAM) based on Neural Radiance Fields (NeRF) enables dense, continuous scene reconstruction. However, existing systems operating with limited online resources struggle to simultaneously construct two types of constraints, namely, compact yet discriminative spatial constraints derived from scene representations and persistent temporal constraints derived from historical observations. To address this challenge, we propose CHOW-SLAM, a dense RGB-D SLAM framework that explicitly constructs these complementary spatial and temporal constraints. Spatially, we propose a compact parametric-hash (P-H) hybrid representation that organizes components based on planes and grids across scales in P and H branches. A unified multi-output decoder further aligns the ray termination distributions induced by TSDF and density, preserving geometry and appearance under a compact parameter budget. Temporally, we propose a complementary overlap-window strategy to prevent optimization from being dominated by short-term overlap or weakly related historical observations. Within a fixed budget, the strategy retains recent frames, selects high-overlap local frames, and introduces temporally distributed historical keyframes. Loss-aware keyframe insertion and bundle adjustment scheduling further adapt optimization to tracking quality. In addition, ORB-based tracking and geometric pose estimation are used for pose initialization, followed by neural rendering optimization to improve tracking stability. Extensive evaluations on multiple datasets demonstrate that CHOW-SLAM outperforms state-of-the-art methods in both scene reconstruction quality and camera tracking accuracy. The source code is available at https://github.com/jinjidexiaohuoban/CHOW-SLAM.
发表机构
- School of Automation Science and Electrical Engineering, Beihang University（北京航空航天大学自动化科学与电气工程学院）
机构由 AI 辅助整理，请以论文原文为准。
