SNH-SLAM: Implicit Dense SLAM based on Scalable Neural-Hash Representation
Lists
Only you see this
Abstract
We present SNH-SLAM, a novel expandable dense neural simultaneous localization and mapping (SLAM) method that constructs a neural field in real-time based on run-time observation. To reach this challenging goal without any scene prior, we utilize instant depth supervision to drive the extension of planar convex hulls, where a single hash table maintains multi-level feature units embedded in the planar convex hulls. This design facilitates high-fidelity, hole-free, and low-memory map reconstruction while adding only a tiny time burden to the training process. Our approach performs mapping by minimizing both RGBD-based re-rendering loss and Truncated Signed Distance Field (TSDF) loss. In addition, for camera tracking, our optimization strategy allows SNH-SLAM to converge faster on the pose estimation and maintain robustness. We evaluate our method on common benchmarks and compare it with existing dense neural RGB-D SLAM methods. The evaluation results show the competitiveness of the SNH-SLAM in tracking accuracy, reconstruction quality, memory usage, and frame processing speed. Project page: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://xiaoshumiao123.github.io</uri>.
BibTeX
@article{li2026snh,
author = {Xiong Li and Zhenyu Wen and Zhanshuo Dong and Haoran Duan and Tianrun Chen and Zhen Hong},
title = {{SNH-SLAM: Implicit Dense SLAM based on Scalable Neural-Hash Representation}},
journal = {IEEE Transactions on Multimedia},
year = {2026},
doi = {10.1109/tmm.2026.3651044},
}Loading related content...