# DL-VINS-Factory: A Modular Framework for Learned Visual Front-Ends in Visual-Inertial SLAM

arXiv: https://arxiv.org/abs/2607.01757 · HTML: https://mlsanity.com/paper/2607.01757/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 32 of its 46 references that are in the map.
- First posted on arXiv 2 Jul 2026.

## Builds on (most cited first, 30 of 32)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019)
- [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [NetVLAD: CNN architecture for weakly supervised place recognition](https://mlsanity.com/paper/1511.07247/) (2015)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator](https://mlsanity.com/paper/1708.03852/) (2017)
- [Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping](https://mlsanity.com/paper/1910.02490/) (2019)
- [Rethinking Visual Geo-localization for Large-Scale Applications](https://mlsanity.com/paper/2204.02287/) (2022)
- [AnyLoc: Towards Universal Visual Place Recognition](https://mlsanity.com/paper/2308.00688/) (2023)
- [MAGSAC++, a fast, reliable and accurate robust estimator](https://mlsanity.com/paper/1912.05909/) (2019)
- [MixVPR: Feature Mixing for Visual Place Recognition](https://mlsanity.com/paper/2303.02190/) (2023)
- [ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation](https://mlsanity.com/paper/2304.03608/) (2023)
- [XFeat: Accelerated Features for Lightweight Image Matching](https://mlsanity.com/paper/2404.19174/) (2024)
- [EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition](https://mlsanity.com/paper/2308.10832/) (2023)
- [Deep Patch Visual SLAM](https://mlsanity.com/paper/2408.01654/) (2024)
- [NTU VIRAL: A Visual-Inertial-Ranging-Lidar Dataset, From an Aerial Vehicle Viewpoint](https://mlsanity.com/paper/2202.00379/) (2022)
- [AirSLAM: An Efficient and Illumination-Robust Point-Line Visual SLAM System](https://mlsanity.com/paper/2408.03520/) (2024)
- [SubT-MRS Dataset: Pushing SLAM Towards All-weather Environments](https://mlsanity.com/paper/2307.07607/) (2023)
- [BotanicGarden: A High-Quality Dataset for Robot Navigation in Unstructured Natural Environments](https://mlsanity.com/paper/2306.14137/) (2023)
- [GCNv2: Efficient Correspondence Prediction for Real-Time SLAM](https://mlsanity.com/paper/1902.11046/) (2019)
- [MAC-VO: Metrics-aware Covariance for Learning-based Stereo Visual Odometry](https://mlsanity.com/paper/2409.09479/) (2024)
- [DXSLAM: A Robust and Efficient Visual SLAM System with Deep Features](https://mlsanity.com/paper/2008.05416/) (2020)
- [Breaking of brightness consistency in optical flow with a lightweight CNN network](https://mlsanity.com/paper/2310.15655/) (2023)
- [OKVIS2-X: Open Keyframe-based Visual-Inertial SLAM Configurable with Dense Depth or LiDAR, and GNSS](https://mlsanity.com/paper/2510.04612/) (2025)
- [Closed-Loop Benchmarking of Stereo Visual-Inertial SLAM Systems: Understanding the Impact of Drift and Latency on Tracking Accuracy](https://mlsanity.com/paper/2003.01317/) (2020)

## Abstract (arXiv)

Deep-learning features excel in visual matching, yet their practical value in tightly coupled visual-inertial SLAM (VI-SLAM) remains insufficiently characterized. We present DL-VINS-Factory, a unified framework that integrates learned feature extractors (ALIKED, RaCo, SuperPoint, XFeat) with either Lucas--Kanade (LK) optical-flow tracking or LightGlue (LG) descriptor matching. All front-ends share a sliding-window Ceres back-end, with optional AnyLoc DINOv2-VLAD loop closure, and 4-DoF pose-graph optimization. We benchmark the system across the four datasets covering indoor, unstructured outdoor, aggressive-motion, and visually degraded conditions. Results show that learned front-ends are viable for real-time embedded VI-SLAM, but are not universally superior to classical tracking. Relative to the corresponding GFTT+LK baseline, ALIKED+LG reduces EuRoC ATE by 5% in monocular odometry and by 7% in stereo with loop-closure. On NTU-VIRAL, where aggressive aerial motion increases inter-frame viewpoint change, ALIKED+LG stereo reduces loop-closed ATE by 12%. In Botanic Garden dataset, optical-flow tracking remains preferable, but learned keypoints still improve over the baseline GFTT, in which SuperPoint+LK reduces grayscale camera ATE by 29%, while RaCo+LK reduces RGB camera ATE by 38%. On SubT-MRS, learned front-ends display varying degree of improvement based on individual cases. With TensorRT acceleration on a Jetson AGX Orin, all valid configurations run in real time between 29--47 FPS in monocular mode and 18--33 FPS in stereo mode for the EuRoC and NTU-VIRAL datasets. AnyLoc further confirms roughly 2--7× more valid loops than BRIEF+DBoW2. The implementation is open-sourced at https://github.com/limshoonkit/DL-VINS-Factory-ROS2/.