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

• URL: http://arxiv.org/abs/2607.15211v1
• Date: Thu, 16 Jul 2026 17:12:58 GMT
• Title: MAGiSt3R: Multi-Agent Feed-forward 3D Reconstruction from Monocular RGB Videos
• Abstract summary: MAGiSt3R is a multi-agent 3D reconstruction framework performing reconstruction and camera tracking for monocular RGB videos at almost 10 FPS.<n>We evaluate MAGiSt3R on both synthetic and real-world datasets, demonstrating its superior reconstruction and camera tracking accuracy compared to state-of-the-art approaches.
• Score: 62.92094310419149
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper presents MAGiSt3R, a multi-agent 3D reconstruction framework performing reconstruction and camera tracking for monocular RGB videos at almost 10 FPS. MAGiSt3R relies on a feed-forward model from the 3R family to process RGB videos and regress local point maps, and on a merging model, MAGMA, that combines local maps at both intra-agent and inter-agent levels to obtain the final global point map. Furthermore, MAGiSt3R performs pose graph optimization to mitigate cumulative camera drift occurring along the feed-forward pipeline. We evaluate MAGiSt3R on both synthetic and real-world datasets, demonstrating its superior reconstruction and camera tracking accuracy compared to state-of-the-art approaches.

Related papers

• ReefMapGS: Enabling Large-Scale Underwater Reconstruction by Closing the Loop Between Multimodal SLAM and Gaussian Splatting [9.554102334590365]
  We propose a 3DGS-based incremental reconstruction framework, ReefMapGS, that builds an initial model from a high certainty region and progressively expands to incorporate the whole scene.<n>We show COLMAP-free 3D reconstruction of two underwater reef sites with complex geometry as well as more accurate global pose estimation of our AUV over survey trajectories spanning up to 700 m.
  arXiv  Detail & Related papers  (2026-04-13T19:32:53Z)
• SR3R: Rethinking Super-Resolution 3D Reconstruction With Feed-Forward Gaussian Splatting [13.122286465610323]
  3D super-resolution (3DSR) aims to reconstruct high-resolution (HR) 3D scenes from low-resolution (LR) multi-view images.<n>Existing methods rely on dense LR inputs and per-scene optimization.<n>We introduce SR3R, a feed-forward framework that directly predicts HR 3DGS representations from sparse LR views.
  arXiv  Detail & Related papers  (2026-02-27T13:45:22Z)
• EAG3R: Event-Augmented 3D Geometry Estimation for Dynamic and Extreme-Lighting Scenes [31.16499311793949]
  E3R is a novel geometry estimation framework that augments pointmap-based reconstruction with asynchronous event streams.<n>EAG3R significantly outperforms state-of-the-art RGB-only baselines across monocular depth estimation, camera pose tracking, and dynamic reconstruction tasks.
  arXiv  Detail & Related papers  (2025-11-30T08:05:28Z)
• Reconstructing 3D Scenes in Native High Dynamic Range [82.90064638813185]
  We present the first method for 3D scene reconstruction that directly models native HDR observations.<n>We propose bf Native High dynamic range 3D Gaussian Splatting (NH-3DGS), which preserves the full dynamic range throughout the reconstruction pipeline.<n>We demonstrate on both synthetic and real multi-view HDR datasets that NH-3DGS significantly outperforms existing methods in reconstruction quality and dynamic range preservation.
  arXiv  Detail & Related papers  (2025-11-17T02:33:31Z)
• MCGS-SLAM: A Multi-Camera SLAM Framework Using Gaussian Splatting for High-Fidelity Mapping [52.99503784067417]
  We present MCGS-SLAM, the first purely RGB-based multi-camera SLAM system built on 3D Gaussian Splatting (3DGS)<n>A multi-camera bundle adjustment (MCBA) jointly refines poses and depths via dense photometric and geometric residuals, while a scale consistency module enforces metric alignment across views.<n>Experiments on synthetic and real-world datasets show that MCGS-SLAM consistently yields accurate trajectories and photorealistic reconstructions.
  arXiv  Detail & Related papers  (2025-09-17T17:27:53Z)
• MapAnything: Universal Feed-Forward Metric 3D Reconstruction [63.79151976126576]
  MapAnything ingests one or more images along with optional geometric inputs such as camera intrinsics, poses, depth, or partial reconstructions.<n>It then directly regresses the metric 3D scene geometry and cameras.<n>MapAnything addresses a broad range of 3D vision tasks in a single feed-forward pass.
  arXiv  Detail & Related papers  (2025-09-16T18:00:14Z)
• PCR-GS: COLMAP-Free 3D Gaussian Splatting via Pose Co-Regularizations [102.0476991174456]
  COLMAP-free 3DGS has attracted increasing attention due to its remarkable performance in reconstructing high-quality 3D scenes from unposed images or videos.<n>We propose PCR-GS, an innovative COLMAP-free 3DGS technique that achieves superior 3D scene modeling and camera pose estimation via camera pose co-regularization.
  arXiv  Detail & Related papers  (2025-07-18T13:09:33Z)
• SEGS-SLAM: Structure-enhanced 3D Gaussian Splatting SLAM with Appearance Embedding [11.512986158947733]
  3D Gaussian splatting (3D-GS) has recently revolutionized novel view synthesis in the simultaneous localization and mapping problem.<n>We propose SEGS-SLAM, a structure-enhanced 3D Gaussian Splatting SLAM, which achieves high-quality photorealistic mapping.
  arXiv  Detail & Related papers  (2025-01-09T13:50:26Z)
• FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction [69.63414788486578]
  FreeSplatter is a scalable feed-forward framework that generates high-quality 3D Gaussians from uncalibrated sparse-view images.<n>Our approach employs a streamlined transformer architecture where self-attention blocks facilitate information exchange.<n>We develop two specialized variants--for object-centric and scene-level reconstruction--trained on comprehensive datasets.
  arXiv  Detail & Related papers  (2024-12-12T18:52:53Z)
• SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos [33.57444419305241]
  SLAM3R is a novel system for real-time, high-quality, dense 3D reconstruction using RGB videos.<n>It seamlessly integrates local 3D reconstruction and global coordinate registration through feed-forward neural networks.<n>It achieves state-of-the-art reconstruction accuracy and completeness while maintaining real-time performance at 20+ FPS.
  arXiv  Detail & Related papers  (2024-12-12T16:08:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.