UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization

• URL: http://arxiv.org/abs/2608.01706v1
• Date: Mon, 03 Aug 2026 05:13:01 GMT
• Title: UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization
• Abstract summary: We introduce UniSim-SLAM, an integrated system that runs lightweight two-view tracking in the richness and performs periodic multi-view submap refinement in the backend.<n>We show that UniSim-SLAM achieves state-of-the-art accuracy in the uncalibrated setting, reducing trajectory error by $38.5% $ on TUM RGB-D and $45.9%$ on 7-Scenes compared to prior best results.
• Score: 10.710770027400883
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent geometric foundation models enable feed-forward inference for SLAM, but their predictions are strongly dependent on the input view set, which leads to geometric inconsistencies and trajectory drift when results are chained over long sequences. Online deployment further exposes a trade-off between the low latency of two-view tracking and the constraint richness of multi-view inference. We introduce UniSim-SLAM, an integrated system that runs lightweight two-view keyframe tracking in the frontend and performs periodic multi-view submap refinement in the backend. To combine predictions defined in heterogeneous local coordinates with inconsistent scales, we formulate a unified multi-level factor graph on $Sim(3)$ that jointly optimizes global keyframe poses and submap poses. The graph integrates temporal view-to-view odometry edges, view-to-submap bridge edges with depth-statistics scale anchoring, and submap-to-submap tie and scale constraints to enforce consistent similarity relations across submaps. Experiments on TUM RGB-D and 7-Scenes show that UniSim-SLAM achieves state-of-the-art accuracy in the uncalibrated setting, reducing trajectory error by $38.5\% $ on TUM RGB-D and $45.9\%$ on 7-Scenes compared to prior best results. Project page: https://vision3d-lab.github.io/unisim-slam/

Related papers

• Self-Geometry: GT-Free and Plug-and-Play Test-Time Adaptation for Geometrically Consistent 3D Vision Foundation Models [12.061080782435013]
  Recent Vision Foundation Models (VFMs) predict depth, camera pose, and pointmap in a single forward pass without per-scene optimization.<n> enforcing explicit multi-view geometric consistency, e.g., through bundle adjustment, is computationally costly and is thus not imposed during VFM pretraining.<n>We propose Self-Geometry, a plug-and-play test-time adaptation pipeline that directly imposes explicit multi-view geometric constraints using 2D pixel correspondences as pseudo ground-truth.
  arXiv  Detail & Related papers  (2026-08-11T09:28:50Z)
• Geometry OR Tracker: Universal Geometric Operating Room Tracking [61.399734016038614]
  In operating rooms (OR), world-scale multi-view 3D tracking supports downstream applications such as surgeon behavior recognition.<n>Camera calibration and RGB-D registration are always unreliable, leading to cross-view geometric inconsistency.<n>We introduce Geometry OR Tracker, a two-stage pipeline that rectifies imprecise calibration into a scaleconsistent and geometrically consistent camera setup.
  arXiv  Detail & Related papers  (2026-02-28T09:21:21Z)
• FeatureSLAM: Feature-enriched 3D gaussian splatting SLAM in real time [11.883404434697809]
  We present a real-time tracking SLAM system that unifies efficient camera tracking and feature-enriched mapping using 3D Gaussian Splatting (3DGS)<n>Our main contribution is integrating dense feature semanticization with semanticization into the novel-view synthesis aligned with a visual foundation model.<n>We obtain 9% lower pose error and 8% higher mapping accuracy compared to recent fixed-set SLAM baselines.
  arXiv  Detail & Related papers  (2026-01-09T11:40:16Z)
• TALO: Pushing 3D Vision Foundation Models Towards Globally Consistent Online Reconstruction [57.46712611558817]
  3D vision foundation models have shown strong generalization in reconstructing key 3D attributes from uncalibrated images through a single feed-forward pass.<n>Recent strategies align consecutive predictions by solving global transformation, yet our analysis reveals their fundamental limitations in assumption validity, local alignment scope, and robustness under noisy geometry.<n>We propose a higher-DOF and long-term alignment framework based on Thin Plate Spline, leveraging globally propagated control points to correct spatially varying inconsistencies.
  arXiv  Detail & Related papers  (2025-12-02T02:22:20Z)
• SING3R-SLAM: Submap-based Indoor Monocular Gaussian SLAM with 3D Reconstruction Priors [80.51557267896938]
  SING3R-SLAM is a globally consistent and compact Gaussian-based dense RGB SLAM framework.<n>We show 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.
  arXiv  Detail & Related papers  (2025-11-21T12:40:55Z)
• ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association [52.34293412010292]
  ViSTA-SLAM is a real-time monocular visual SLAM system that operates without requiring camera closures.<n>Our approach achieves superior performance in both camera tracking and dense 3D reconstruction quality.
  arXiv  Detail & Related papers  (2025-09-01T16:12:23Z)
• ${C}^{3}$-GS: Learning Context-aware, Cross-dimension, Cross-scale Feature for Generalizable Gaussian Splatting [16.868578618340262]
  Generalizable Gaussian Splatting aims to synthesize novel views for unseen scenes without per-scene optimization.<n>We propose $mathbfC3$-GS, a framework that enhances feature learning by incorporating context-aware, cross-dimension, and cross-scale constraints.<n>Our architecture integrates three lightweight modules into a unified rendering pipeline, improving feature fusion and enabling synthesis without requiring additional supervision.
  arXiv  Detail & Related papers  (2025-08-28T13:12:18Z)
• Pseudo Depth Meets Gaussian: A Feed-forward RGB SLAM Baseline [64.42938561167402]
  We propose an online 3D reconstruction method using 3D Gaussian-based SLAM, combined with a feed-forward recurrent prediction module.<n>This approach replaces slow test-time optimization with fast network inference, significantly improving tracking speed.<n>Our method achieves performance on par with the state-of-the-art SplaTAM, while reducing tracking time by more than 90%.
  arXiv  Detail & Related papers  (2025-08-06T16:16:58Z)
• TVG-SLAM: Robust Gaussian Splatting SLAM with Tri-view Geometric Constraints [22.121665995381324]
  TVG-SLAM is a robust RGB-only 3DGS SLAM system that leverages a novel tri-view geometry paradigm to ensure consistent tracking and high-quality mapping.<n>Our method improves tracking robustness, reducing the average Absolute Trajectory Error (ATE) by 69.0% while achieving state-of-the-art rendering quality.
  arXiv  Detail & Related papers  (2025-06-29T12:31:05Z)
• Parallel Structure from Motion for UAV Images via Weighted Connected Dominating Set [5.17395782758526]
  This paper proposes an algorithm to extract the global model for cluster merging and designs a parallel SfM solution to achieve efficient and accurate UAV image orientation. The experimental results demonstrate that the proposed parallel SfM can achieve 17.4 times efficiency improvement and comparative orientation accuracy.
  arXiv  Detail & Related papers  (2022-06-23T06:53:06Z)
• TANDEM: Tracking and Dense Mapping in Real-time using Deep Multi-view Stereo [55.30992853477754]
  We present TANDEM, a real-time monocular tracking and dense framework. For pose estimation, TANDEM performs photometric bundle adjustment based on a sliding window of alignments. TANDEM shows state-of-the-art real-time 3D reconstruction performance.
  arXiv  Detail & Related papers  (2021-11-14T19:01:02Z)

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.