CHOW-SLAM: Compact Hybrid Representation with Complementary Overlap Window Optimization for RGB-D SLAM
2026-08-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors present CHOW-SLAM, a system that helps robots or devices create detailed 3D maps of environments using RGB-D cameras while figuring out their own location. They tackle the problem of balancing two important types of information: spatial clues from the scene itself and timing clues from past observations. Their method uses a special way to represent space with planes and grids, plus a strategy to smartly choose which past frames to use for better mapping and tracking. Tests show their approach gives better 3D maps and more accurate camera positions than previous methods.
Simultaneous Localization and Mapping (SLAM)Neural Radiance Fields (NeRF)RGB-D cameraParametric-hash representationTemporal constraintsSpatial constraintsPose trackingBundle adjustmentNeural renderingKeyframe selection
Authors
Wenxuan Ji, Jin Xiao, Xiaoguang Hu, Jiaqi Shi, Zichong Jia, Baochang Zhang
Abstract
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.