SLAM in Low-Light Environments: Project Report

Hugging Face Daily Papers Papers
low-light slam benchmarking rgb-camera slam-systems robotics computer-vision

Summary

This paper benchmarks six SLAM systems under low-light conditions using five LaMARia sequences, finding that only Kimera-VIO tracks all sequences to completion while other RGB-only systems fail or diverge, highlighting the need for inertial fusion and global optimization.

Simultaneous localization and mapping (SLAM) is one of the fundamental problems in robotics, as it enables autonomous operations in real-world scenarios. Under low illumination, reduced contrast, sensor noise, and motion blur degrade both feature extraction and feature matching, while compensating with LiDAR, depth, or thermal sensors raises cost, power draw, and integration complexity. Existing benchmarks remain dominated by well-lit indoor or daylight sequences, leaving open how far SLAM with standard RGB cameras can be pushed in the dark. We benchmark six systems spanning the feature-based, direct, filter-based, and learning-based paradigms - ORB-SLAM3, DSO, Kimera-VIO, OpenVINS, DPVO, and DPV-SLAM - on five LaMARia sequences of varying difficulty and illumination, reporting absolute and relative pose error alongside control-point recall. Kimera-VIO is the only system to track all five sequences to completion, combining the lowest relative pose error with steadily growing absolute error due to the absence of loop closure; DPVO and DPV-SLAM never lose tracking but incur absolute errors of roughly 100 m under low light; and the classical monocular pipelines (ORB-SLAM3, DSO) together with the filter-based OpenVINS fail outright or diverge on most of the harder and low-light sequences. The results suggest that RGB-only SLAM maintains stable low-light tracking only when both inertial fusion and global optimization are present. Closing the remaining gap will likely require low-light-specific learned front-ends or a return to complementary sensing.
Original Article
View Cached Full Text

Cached at: 07/24/26, 05:07 AM

Paper page - SLAM in Low-Light Environments: Project Report

Source: https://huggingface.co/papers/2607.17699

Abstract

Simultaneouslocalizationandmapping(SLAM)isoneofthefundamentalproblemsinrobotics,asitenablesautonomousoperationsinreal-worldscenarios.Underlowillumination,reducedcontrast,sensornoise,andmotionblurdegradebothfeatureextractionandfeaturematching,whilecompensatingwithLiDAR,depth,orthermalsensorsraisescost,powerdraw,andintegrationcomplexity.Existingbenchmarksremaindominatedbywell-litindoorordaylightsequences,leavingopenhowfarSLAMwithstandardRGBcamerascanbepushedinthedark.Webenchmarksixsystemsspanningthefeature-based,direct,filter-based,andlearning-basedparadigms-ORB-SLAM3,DSO,Kimera-VIO,OpenVINS,DPVO,andDPV-SLAM-onfiveLaMARiasequencesofvaryingdifficultyandillumination,reportingabsoluteandrelativeposeerroralongsidecontrol-pointrecall.Kimera-VIOistheonlysystemtotrackallfivesequencestocompletion,combiningthelowestrelativeposeerrorwithsteadilygrowingabsoluteerrorduetotheabsenceofloopclosure;DPVOandDPV-SLAMneverlosetrackingbutincurabsoluteerrorsofroughly100munderlowlight;andtheclassicalmonocularpipelines(ORB-SLAM3,DSO)togetherwiththefilter-basedOpenVINSfailoutrightordivergeonmostoftheharderandlow-lightsequences.TheresultssuggestthatRGB-onlySLAMmaintainsstablelow-lighttrackingonlywhenbothinertialfusionandglobaloptimizationarepresent.Closingtheremaininggapwilllikelyrequirelow-light-specificlearnedfront-endsorareturntocomplementarysensing.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2607\.17699

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.17699 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.17699 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.17699 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?

Hugging Face Daily Papers

SpatialScout introduces a benchmark evaluating vision-language model agents on active object-level 3D mapping across 80 indoor scenes, revealing that even the strongest model, Claude Opus 5.5, achieves only 41.71% mean overlap, highlighting major gaps in precise metric map construction.

Toward Robust and 3D-Aware RGB-NIR Imaging in the Dark

Hugging Face Daily Papers

This paper presents a 3D-aware neural approach for RGB-NIR low-light imaging that fuses extremely noisy RGB observations with NIR cues in 3D space, eliminating the need for clean RGB supervision and improving robustness across different noise levels.

Towards Real-Time and Adaptable LiDAR Scene Completion

Hugging Face Daily Papers

RapidLiDAR introduces a real-time LiDAR scene completion method using adaptive initialization and multi-scale reconstruction, achieving state-of-the-art performance 2.3 times faster to match automotive LiDAR rates.

NAVER LABS Europe Submission to the Instruction-following 2026 Short Track

arXiv cs.CL

This paper describes NAVER LABS Europe's submission to the IWSLT 2026 instruction-following short track, improving upon their previous winning system by using a new speech projector (SpeechMapper) trained solely on ASR data and augmenting training with a synthetic SQA dataset (fakACL). The resulting system ties for first place in the constrained track while using a weaker LLM backbone.