Uni-SLAM: Uncertainty-Aware Neural Implicit SLAM for Real-Time Dense Indoor Scene Reconstruction

TL;DR

Uni-SLAM introduces an uncertainty-aware neural implicit SLAM system that enhances real-time dense indoor scene reconstruction, especially for thin structures, by reweighting loss functions and employing a hash grid-based representation.

Contribution

It presents a novel uncertainty-based reweighting method and a decoupled hash grid representation for improved accuracy and real-time performance in indoor scene reconstruction.

Findings

Achieves state-of-the-art tracking and mapping accuracy.

Reduces depth L1 error by 25%.

Improves reconstruction of thin structures with 66.86% completion rate within 1 cm.

Abstract

Neural implicit fields have recently emerged as a powerful representation method for multi-view surface reconstruction due to their simplicity and state-of-the-art performance. However, reconstructing thin structures of indoor scenes while ensuring real-time performance remains a challenge for dense visual SLAM systems. Previous methods do not consider varying quality of input RGB-D data and employ fixed-frequency mapping process to reconstruct the scene, which could result in the loss of valuable information in some frames. In this paper, we propose Uni-SLAM, a decoupled 3D spatial representation based on hash grids for indoor reconstruction. We introduce a novel defined predictive uncertainty to reweight the loss function, along with strategic local-to-global bundle adjustment. Experiments on synthetic and real-world datasets demonstrate that our system achieves state-of-the-art tracking and mapping accuracy while maintaining real-time performance. It significantly improves over current methods with a 25% reduction in depth L1 error and a 66.86% completion rate within 1 cm on the Replica dataset, reflecting a more accurate reconstruction of thin structures. Project page: https://shaoxiang777.github.io/project/uni-slam/