# FD-SLAM: 3-D Reconstruction Using Features and Dense Matching

arXiv: https://arxiv.org/abs/2203.13861 · HTML: https://mlsanity.com/paper/2203.13861/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 39 references that are in the map.
- First posted on arXiv 25 Mar 2022.

## Builds on (most cited first, 11 of 11)

- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions](https://mlsanity.com/paper/1603.08182/) (2016)
- [PointNetVLAD: Deep Point Cloud Based Retrieval for Large-Scale Place Recognition](https://mlsanity.com/paper/1804.03492/) (2018)
- [PPFNet: Global Context Aware Local Features for Robust 3D Point Matching](https://mlsanity.com/paper/1802.02669/) (2018)
- [Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planning](https://mlsanity.com/paper/1611.03631/) (2016)
- [BundleFusion: Real-time Globally Consistent 3D Reconstruction using On-the-fly Surface Re-integration](https://mlsanity.com/paper/1604.01093/) (2016)
- [DH3D: Deep Hierarchical 3D Descriptors for Robust Large-Scale 6DoF Relocalization](https://mlsanity.com/paper/2007.09217/) (2020)
- [Voxgraph: Globally Consistent, Volumetric Mapping using Signed Distance Function Submaps](https://mlsanity.com/paper/2004.13154/) (2020)
- [Flex-Convolution (Million-Scale Point-Cloud Learning Beyond Grid-Worlds)](https://mlsanity.com/paper/1803.07289/) (2018)
- [Efficient Online Surface Correction for Real-time Large-Scale 3D Reconstruction](https://mlsanity.com/paper/1709.03763/) (2017)

## Built on by (most cited first, 17 of 17)

- [Point-SLAM: Dense Neural Point Cloud-based SLAM](https://mlsanity.com/paper/2304.04278/) (2023)
- [ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields](https://mlsanity.com/paper/2211.11704/) (2022)
- [Gaussian-SLAM: Photo-realistic Dense SLAM with Gaussian Splatting](https://mlsanity.com/paper/2312.10070/) (2023)
- [Vox-Fusion: Dense Tracking and Mapping with Voxel-based Neural Implicit Representation](https://mlsanity.com/paper/2210.15858/) (2022)
- [Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians](https://mlsanity.com/paper/2405.16544/) (2024)
- [LoopSplat: Loop Closure by Registering 3D Gaussian Splats](https://mlsanity.com/paper/2408.10154/) (2024)
- [Loopy-SLAM: Dense Neural SLAM with Loop Closures](https://mlsanity.com/paper/2402.09944/) (2024)
- [GlORIE-SLAM: Globally Optimized RGB-only Implicit Encoding Point Cloud SLAM](https://mlsanity.com/paper/2403.19549/) (2024)
- [PVO: Panoptic Visual Odometry](https://mlsanity.com/paper/2207.01610/) (2022)
- [iDF-SLAM: End-to-End RGB-D SLAM with Neural Implicit Mapping and Deep Feature Tracking](https://mlsanity.com/paper/2209.07919/) (2022)
- [Vox-Fusion++: Voxel-based Neural Implicit Dense Tracking and Mapping with Multi-maps](https://mlsanity.com/paper/2403.12536/) (2024)
- [Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space](https://mlsanity.com/paper/2507.00392/) (2025)
- [AEGIS-Net: Attention-guided Multi-Level Feature Aggregation for Indoor Place Recognition](https://mlsanity.com/paper/2312.09538/) (2023)
- [PoCo: Point Context Cluster for RGBD Indoor Place Recognition](https://mlsanity.com/paper/2404.02885/) (2024)
- [VIPeR: Visual Incremental Place Recognition with Adaptive Mining and Continual Learning](https://mlsanity.com/paper/2407.21416/) (2024)
- [Deblur Gaussian Splatting SLAM](https://mlsanity.com/paper/2503.12572/) (2025)
- [VFM-Recon: Unlocking Cross-Domain Scene-Level Neural Reconstruction with Scale-Aligned Foundation Priors](https://mlsanity.com/paper/2603.12657/) (2026)

## Abstract (arXiv)

It is well known that visual SLAM systems based on dense matching are locally accurate but are also susceptible to long-term drift and map corruption. In contrast, feature matching methods can achieve greater long-term consistency but can suffer from inaccurate local pose estimation when feature information is sparse. Based on these observations, we propose an RGB-D SLAM system that leverages the advantages of both approaches: using dense frame-to-model odometry to build accurate sub-maps and on-the-fly feature-based matching across sub-maps for global map optimisation. In addition, we incorporate a learning-based loop closure component based on 3-D features which further stabilises map building. We have evaluated the approach on indoor sequences from public datasets, and the results show that it performs on par or better than state-of-the-art systems in terms of map reconstruction quality and pose estimation. The approach can also scale to large scenes where other systems often fail.