# F2 SLAM: Turning Feed-Forward Geometry into Persistent Factors for SLAM

arXiv: https://arxiv.org/abs/2610.05207 · HTML: https://mlsanity.com/paper/2610.05207/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 33 references that are in the map.
- First posted on arXiv 4 Oct 2026.

## Builds on (most cited first, 28 of 28)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [3D Reconstruction with Spatial Memory](https://mlsanity.com/paper/2408.16061/) (2024)
- [MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors](https://mlsanity.com/paper/2412.12392/) (2024)
- [NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM](https://mlsanity.com/paper/2302.03594/) (2023)
- [Streaming 4D Visual Geometry Transformer](https://mlsanity.com/paper/2507.11539/) (2025)
- [VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold](https://mlsanity.com/paper/2505.12549/) (2025)
- [GO-SLAM: Global Optimization for Consistent 3D Instant Reconstruction](https://mlsanity.com/paper/2309.02436/) (2023)
- [SLAM3R: Real-Time Dense Scene Reconstruction from Monocular RGB Videos](https://mlsanity.com/paper/2412.09401/) (2024)
- [Deep Patch Visual SLAM](https://mlsanity.com/paper/2408.01654/) (2024)
- [LDSO: Direct Sparse Odometry with Loop Closure](https://mlsanity.com/paper/1808.01111/) (2018)
- [LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction](https://mlsanity.com/paper/2604.14141/) (2026)
- [VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstruction](https://mlsanity.com/paper/2601.19887/) (2026)
- [Advances in Global Solvers for 3D Vision](https://mlsanity.com/paper/2602.14662/) (2026)
- [SLAM-Former: Putting SLAM into One Transformer](https://mlsanity.com/paper/2509.16909/) (2025)
- [Flow3r: Factored Flow Prediction for Scalable Visual Geometry Learning](https://mlsanity.com/paper/2602.20157/) (2026)
- [VGGT-SLAM++](https://mlsanity.com/paper/2604.06830/) (2026)
- [FrameVGGT: Coherence-Preserving Memory for Bounded Streaming Geometry](https://mlsanity.com/paper/2603.07690/) (2026)
- [MyGO-Splat: Multi-Objective Closed-Loop Geometric Feedback for RGB-Only Gaussian SLAM](https://mlsanity.com/paper/2606.29738/) (2026)
- [LR-SGS: Robust LiDAR-Reflectance-Guided Salient Gaussian Splatting for Self-Driving Scene Reconstruction](https://mlsanity.com/paper/2603.12647/) (2026)
- [PanoImager: Geometry-Guided Novel View Synthesis and Reconstruction from Sparse Panoramic Views](https://mlsanity.com/paper/2606.27071/) (2026)

## Abstract (arXiv)

Feed-forward 3D models provide strong multi-view geometric priors, while on- line simultaneous localization and mapping (SLAM) relies mainly on local mea- surements and can accumulate drift over long sequences. Existing attempts to combine the two typically treat feed-forward predictions as an external geomet- ric state that is aligned or fused with the online estimate after the fact, which keeps broader multi-view evidence outside the optimizer that refines the SLAM state. We present F2SLAM, which instead converts feed-forward geometry di- rectly into optimization-native target-weight measurements attached to a persis- tent dense factor graph. A high-frequency stream maintains local tracking con- straints and graph connectivity, while a low-frequency stream uses wider multi- view context to selectively refresh existing measurements after a state-consistency check. Both streams constrain the same poses, inverse depths, and optional cam- era intrinsics through a single dense bundle adjustment. Experiments on multiple benchmarks demonstrate consistently strong trajectory estimation and improved dense reconstruction in both calibrated and uncalibrated settings. Notably, the uncalibrated configuration reduces the average ATE RMSE from 0.030 m for the strongest feed-forward baseline to 0.002 m on the Replica dataset.