Pith. sign in

REVIEW 12 cited by

How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Survey

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2402.13255 v3 pith:SB72Y5DA submitted 2024-02-20 cs.CV cs.RO

Fabio Tosi , Youmin Zhang , Ziren Gong , Erik Sandström , Stefano Mattoccia , Martin R. Oswald , Matteo Poggi This is my paper
classification cs.CVcs.RO
keywords slamcomprehensiveevolutionfieldsgaussiannerfsprogressradiance
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Over the past two decades, research in the field of Simultaneous Localization and Mapping (SLAM) has undergone a significant evolution, highlighting its critical role in enabling autonomous exploration of unknown environments. This evolution ranges from hand-crafted methods, through the era of deep learning, to more recent developments focused on Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (3DGS) representations. Recognizing the growing body of research and the absence of a comprehensive survey on the topic, this paper aims to provide the first comprehensive overview of SLAM progress through the lens of the latest advancements in radiance fields. It sheds light on the background, evolutionary path, inherent strengths and limitations, and serves as a fundamental reference to highlight the dynamic progress and specific challenges.

Discussion (0). Sign in to comment.

Forward citations

Cited by 12 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Immediate 3D Gaussian Splat Reconstruction of Unordered Input with Global Consistency

    cs.CV 2026-07 conditional novelty 7.0 of 10

    A pipeline that performs immediate-feedback 3D Gaussian Splatting reconstruction from unordered image streams, with loop closure and a progressive hierarchy providing global consistency.

  2. MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos

    cs.CV 2026-07 conditional novelty 6.0 of 10

    MAGiSt3R is a multi-agent feed-forward 3D reconstruction system using a learned submap-merging model (MAGMA) and pose graph optimization to align local maps from multiple monocular RGB cameras into one consistent map ...

  3. LEGO-SLAM: Language-Embedded Gaussian Optimization SLAM

    cs.CV 2025-11 conditional novelty 6.0 of 10

    A 3D Gaussian Splatting SLAM system learns compact 16-dim language features per Gaussian, enabling real-time open-vocabulary mapping, semantic pruning, and language-based loop closure.

  4. DyPho-SLAM : Real-time Photorealistic SLAM in Dynamic Environments

    cs.RO 2025-08 conditional novelty 6.0 of 10

    DyPho-SLAM uses prior-image masks and adaptive feature selection to keep camera tracking accurate while building a photorealistic static 3D map in real time.

  5. DINO-SLAM: DINO-informed RGB-D SLAM for Neural Implicit and Explicit Representations

    cs.CV 2025-07 conditional novelty 6.0 of 10

    Geometry-enriched DINO features improve mapping, rendering, and tracking in both NeRF-based and 3D Gaussian splatting SLAM pipelines on indoor benchmarks.

  6. AntiGrounding: Lifting Robotic Actions into VLM Representation Space for Decision Making

    cs.RO 2025-06 conditional novelty 6.0 of 10

    AntiGrounding lifts candidate robot trajectories into the VLM's visual space via multi-view rendering and structured VQA, and reports 57.5% average success across eight manipulation tasks, beating three intermediate-r...

  7. GeoGS-SLAM: Online Monocular Reconstruction Using Gaussian Splatting with Geometric Priors

    cs.RO 2026-07 conditional novelty 5.0 of 10

    An online monocular SLAM system that samples 3D Gaussians from RGB plus VGGT geometric priors and jointly optimizes poses and map with photometric and geometric losses plus loop closure, beating prior monocular 3DGS a...

  8. Enhanced Velocity Field Modeling for Gaussian Video Reconstruction

    cs.CV 2025-07 conditional novelty 5.0 of 10

    Velocity field rendering with flow-based losses and flow-assisted densification lifts dynamic Gaussian novel-view PSNR by about 2.5 dB on Nvidia-long and Neu3D.

  9. Stereo 3D Gaussian Splatting SLAM for Outdoor Urban Scenes

    cs.RO 2025-07 conditional novelty 5.0 of 10

    BGS-SLAM combines ORB-SLAM2 tracking with 3D Gaussian splatting mapping supervised by pretrained stereo depth networks, and reports improved outdoor mapping and tracking over the tested 3DGS-SLAM baselines.

  10. LRSLAM: Low-rank Representation of Signed Distance Fields in Dense Visual SLAM System

    cs.CV 2025-06 conditional novelty 5.0 of 10

    LRSLAM couples CP decomposition for geometry with a new Six-axis decomposition for appearance, yielding a dense RGB-D SLAM with linear memory growth and accuracy competitive with ESLAM.

  11. Dy3DGS-SLAM: Monocular 3D Gaussian Splatting SLAM for Dynamic Environments

    cs.CV 2025-06 conditional novelty 5.0 of 10

    Dy3DGS-SLAM fuses optical flow and monocular depth masks to perform 3D Gaussian Splatting SLAM with a single RGB camera in scenes with moving objects, reporting lower trajectory error than several RGB-D baselines.

  12. Reconstructing 4D Spatial Intelligence: A Survey

    cs.CV 2025-07 accept novelty 4.0 of 10

    A review that classifies 4D scene reconstruction methods into five progressive levels: low-level cues, scene components, dynamic scenes, interactions, and physics.

Pith tools