arXiv:2511.17207v1 Announce Type: new 
Abstract: Recent advances in dense 3D reconstruction enable the accurate capture of local geometry; however, integrating them into SLAM is challenging due to drift and redundant point maps, which limit efficiency and downstream tasks, such as novel view synthesis. To address these issues, we propose SING3R-SLAM, a globally consistent and compact Gaussian-based dense RGB SLAM framework. The key idea is to combine locally consistent 3D reconstructions with a unified global Gaussian representation that jointly refines scene geometry and camera poses, enabling efficient and versatile 3D mapping for multiple downstream applications. SING3R-SLAM first builds locally consistent submaps through our lightweight tracking and reconstruction module, and then progressively aligns and fuses them into a global Gaussian map that enforces cross-view geometric consistency. This global map, in turn, provides feedback to correct local drift and enhance the robustness of tracking. Extensive experiments demonstrate that SING3R-SLAM achieves state-of-the-art tracking, 3D reconstruction, and novel view rendering, resulting in over 12% improvement in tracking and producing finer, more detailed geometry, all while maintaining a compact and memory-efficient global representation on real-world datasets.

SING3R-SLAM هو إطار جديد يعتمد على Gaussian SLAM RGB الكثيف الذي يدمج إعادة بناء ثلاثية الأبعاد المتسقة محليًا مع تمثيل غاوسي عالمي، مما يعالج التحديات المتعلقة بالانحراف وخرائط النقاط الزائدة. تتيح هذه الطريقة المبتكرة رسم خرائط ثلاثية الأبعاد بكفاءة ومرونة لمجموعة متنوعة من التطبيقات، مما يعزز هندسة المشهد ودقة أوضاع الكاميرا.

SING3R-SLAM es un nuevo marco de SLAM RGB denso basado en Gaussianas que integra reconstrucciones 3D localmente consistentes con una representación gaussiana global, abordando desafíos como la deriva y los mapas de puntos redundantes. Este enfoque innovador permite un mapeo 3D eficiente y versátil para diversas aplicaciones, mejorando la geometría de la escena y la precisión de las poses de la cámara.

SING3R-SLAM est un nouveau cadre SLAM RGB dense basé sur un modèle gaussien qui intègre des reconstructions 3D localement cohérentes avec une représentation gaussienne globale, abordant les défis liés à la dérive et aux cartes de points redondantes. Cette approche innovante permet un mappage 3D efficace et polyvalent pour diverses applications, améliorant la géométrie de la scène et la précision des poses de caméra.

SING3R-SLAM is a newly proposed Gaussian-based dense RGB SLAM framework that integrates locally consistent 3D reconstructions with a global Gaussian representation, addressing challenges in drift and redundant point maps. This innovative approach enables efficient and versatile 3D mapping for various applications, enhancing scene geometry and camera pose accuracy.

SING3R-SLAM: Submap-based Indoor Monocular Gaussian SLAM with 3D Reconstruction Priors

arXiv:2601.08414v1 Announce Type: new 
Abstract: Real-time multi-camera 3D reconstruction is crucial for 3D perception, immersive interaction, and robotics. Existing methods struggle with multi-view fusion, camera extrinsic uncertainty, and scalability for large camera setups. We propose SPARK, a self-calibrating real-time multi-camera point cloud reconstruction framework that jointly handles point cloud fusion and extrinsic uncertainty. SPARK consists of: (1) a geometry-aware online extrinsic estimation module leveraging multi-view priors and enforcing cross-view and temporal consistency for stable self-calibration, and (2) a confidence-driven point cloud fusion strategy modeling depth reliability and visibility at pixel and point levels to suppress noise and view-dependent inconsistencies. By performing frame-wise fusion without accumulation, SPARK produces stable point clouds in dynamic scenes while scaling linearly with the number of cameras. Extensive experiments on real-world multi-camera systems show that SPARK outperforms existing approaches in extrinsic accuracy, geometric consistency, temporal stability, and real-time performance, demonstrating its effectiveness and scalability for large-scale multi-camera 3D reconstruction.

تم تقديم إطار عمل جديد يسمى SPARK لجمع سحب النقاط في الوقت الفعلي وبشكل قابل للتوسع باستخدام كاميرات متعددة، حيث يتناول التحديات المتعلقة بإعادة بناء ثلاثية الأبعاد، وخاصة إدارة عدم اليقين الخارجي ودمج وجهات النظر المتعددة. يجمع هذا النهج المبتكر بين تقدير خارجي على الإنترنت مدرك للهندسة واستراتيجية دمج سحب النقاط المعتمدة على الثقة، مما يسمح بإنشاء سحب نقاط مستقرة في البيئات الديناميكية.

Se ha presentado un nuevo marco llamado SPARK para la agregación de nubes de puntos en tiempo real y a gran escala con múltiples cámaras, abordando los desafíos de la reconstrucción 3D, especialmente en la gestión de la incertidumbre extrínseca y la fusión de múltiples vistas. Este enfoque innovador combina una estimación extrínseca en línea consciente de la geometría con una estrategia de fusión de nubes de puntos impulsada por la confianza, lo que permite la generación de nubes de puntos estables en entornos dinámicos.

Un nouveau cadre nommé SPARK a été introduit pour l'agrégation de nuages de points multi-caméras en temps réel et à grande échelle, abordant les défis de la reconstruction 3D, en particulier la gestion de l'incertitude extrinsèque et de la fusion multi-vues. Cette approche innovante combine une estimation extrinsèque en ligne consciente de la géométrie avec une stratégie de fusion de nuages de points basée sur la confiance, permettant la génération de nuages de points stables dans des environnements dynamiques.

A new framework named SPARK has been introduced for scalable real-time multi-camera point cloud aggregation, addressing challenges in 3D reconstruction, particularly in handling extrinsic uncertainty and multi-view fusion. This innovative approach combines geometry-aware online extrinsic estimation with a confidence-driven point cloud fusion strategy, enabling stable point cloud generation in dynamic environments.

SING3R-SLAM: Submap-based Indoor Monocular Gaussian SLAM with 3D Reconstruction Priors

Was this article worth reading? Share it

LucidQuery AI

Deptho.ai

Attentive AI

OneSky Localization Agent

OpenL Translator

Zemith-3bda3b

Ready to build your own newsroom?