PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
May 14, 2026ISPRS International Journal of Geo-Information0 citationsOpen Access

Dense SLAM System Based on Hybrid Representation of Neural Point Cloud and Multi-Resolution Voxel (NPMV-SLAM)

View Full Paper
QHQicheng HuangRZRuiju ZhangJWJian Wang

Key Points

  • The aim is to develop a dense SLAM system that improves tracking accuracy and reconstruction quality using neural implicit methods.
  • Proposed NPMV-SLAM system integrates multi-resolution voxel grids with feature point clouds.
  • Implemented an adaptive sampling strategy that utilizes point cloud density to enhance scene scalability.
  • Conducted experiments using the Replica and TUM datasets to evaluate system performance.
  • Achieved notable improvements in tracking accuracy and rendering quality compared to traditional SLAM approaches.
  • Demonstrated enhanced global reconstruction completeness with reduced computational redundancy.
  • Observed significant performance gains in mapping accuracy across multiple indoor scenes.

Abstract

We propose NPMV-SLAM, an RGB-Depth neural implicit dense SLAM system based on multi-resolution voxels and feature point clouds. The method demonstrates exceptional performance in tracking accuracy and reconstruction quality, aiming to address the shortcomings of traditional visual SLAM in texture detail modeling and geometric consistency, as well as the limitations of existing neural implicit methods in real-time performance and scene scalability. (1) We innovatively propose a position-enhanced encoding mechanism that fuses multi-resolution hash voxel grids with feature point clouds. This design fully leverages the high sensitivity of point clouds to high-frequency geometric details and the global structural continuity provided by voxels, achieving complementary advantages during network training and inference, thereby comprehensively enhancing the system’s reconstruction generalization capability. (2) Furthermore, we design an adaptive sampling strategy guided by point cloud density priors. This strategy fundamentally alleviates the core issue of insufficient scene scalability through data-driven online point cloud reconstruction. By filtering out invalid, non-surface sampling points, it concentrates computational resources on object surface regions, significantly reducing computational redundancy in empty areas, and achieves efficient point cloud spatial indexing with the aid of a vector database similarity search algorithm. While maintaining operational efficiency, our method significantly improves both detailed reconstruction capability and global reconstruction completeness. Experiments conducted on multiple indoor scenes from the Replica and TUM datasets show that our approach achieves notable improvements in tracking accuracy, rendering quality, and mapping accuracy, successfully balancing precision and efficiency.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Huang et al. (2026) studied this question.

synapsesocial.com/papers/6a0567bca550a87e60a1ff13https://doi.org/10.3390/ijgi15050210
Ask AI
Helpful
Bookmark
Share
View Full Paper