UncLe-SLAM: Uncertainty Learning for Dense Neural SLAM
We present an uncertainty learning framework for dense neural simultaneous localization and mapping (SLAM). Estimating pixel-wise uncertainties for the depth input of dense SLAM methods allows re-weighing the tracking and mapping losses towards image regions that contain more suitable information that is more reliable for SLAM. To this end, we propose an online framework for sensor uncertainty estimation that can be trained in a self-supervised manner from only 2D input data. We further discuss the advantages of the uncertainty learning for the case of multi-sensor input. Extensive analysis, experimentation, and ablations show that our proposed modeling paradigm improves both mapping and tracking accuracy and often performs better than alternatives that require ground truth depth or 3D. Our experiments show that we achieve a 38\% and 27\% lower absolute trajectory tracking error (ATE) on the 7-Scenes and TUM-RGBD datasets respectively. On the popular Replica dataset using two types of depth sensors, we report an 11\% F1-score improvement on RGBD SLAM compared to the recent state-of-the-art neural implicit approaches. Source code: https://github.com/kev-in-ta/UncLe-SLAM.
Code (1)
Tasks
Simultaneous Localization and MappingSimilar Papers 제목 키워드 기반
Probabilistic Volumetric Fusion for Dense Monocular SLAM
We present a novel method to reconstruct 3D scenes from images by leveraging deep dense monocular SLAM and fast uncertainty propagation. The proposed approach is able to 3D reconstruct scenes densely, accurately, and in …
CG-SLAM: Efficient Dense RGB-D SLAM in a Consistent Uncertainty-aware 3D Gaussian Field
Recently neural radiance fields (NeRF) have been widely exploited as 3D representations for dense simultaneous localization and mapping (SLAM). Despite their notable successes in surface modeling and novel view synthesis…
NeRFNovel View SynthesisSimultaneous Localization and MappingCodeMapping: Real-Time Dense Mapping for Sparse SLAM using Compact Scene Representations
We propose a novel dense mapping framework for sparse visual SLAM systems which leverages a compact scene representation. State-of-the-art sparse visual SLAM systems provide accurate and reliable estimates of the camera …
3D ReconstructionDepth EstimationScene UnderstandingWildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments
We present WildGS-SLAM, a robust and efficient monocular RGB SLAM system designed to handle dynamic environments by leveraging uncertainty-aware geometric mapping. Unlike traditional SLAM systems, which assume static sce…
NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fields
We propose a novel geometric and photometric 3D mapping pipeline for accurate and real-time scene reconstruction from monocular images. To achieve this, we leverage recent advances in dense monocular SLAM and real-time h…
NeRF