# LiftFeat: 3D Geometry-Aware Local Feature Matching arXiv: https://arxiv.org/abs/2505.03422 ยท HTML: https://mlsanity.com/paper/2505.03422/ ## Key facts - Cited by 12 papers in the map (data through 14 Oct 2026). - Builds on 30 of its 43 references that are in the map. - First posted on arXiv 6 May 2025. ## Builds on (most cited first, 30 of 30) - [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014) - [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017) - [SuperGlue: Learning Feature Matching with Graph Neural Networks](https://mlsanity.com/paper/1911.11763/) (2019) - [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024) - [SuperPoint: Self-Supervised Interest Point Detection and Description](https://mlsanity.com/paper/1712.07629/) (2017) - [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016) - [MegaDepth: Learning Single-View Depth Prediction from Internet Photos](https://mlsanity.com/paper/1804.00607/) (2018) - [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023) - [From Coarse to Fine: Robust Hierarchical Localization at Large Scale](https://mlsanity.com/paper/1812.03506/) (2018) - [D2-Net: A Trainable CNN for Joint Detection and Description of Local Features](https://mlsanity.com/paper/1905.03561/) (2019) - [DISK: Learning local features with policy gradient](https://mlsanity.com/paper/2006.13566/) (2020) - [HPatches: A benchmark and evaluation of handcrafted and learned local descriptors](https://mlsanity.com/paper/1704.05939/) (2017) - [MAGSAC++, a fast, reliable and accurate robust estimator](https://mlsanity.com/paper/1912.05909/) (2019) - [XFeat: Accelerated Features for Lightweight Image Matching](https://mlsanity.com/paper/2404.19174/) (2024) - [FastDepth: Fast Monocular Depth Estimation on Embedded Systems](https://mlsanity.com/paper/1903.03273/) (2019) - [Orbeez-SLAM: A Real-time Monocular Visual SLAM with ORB Features and NeRF-realized Mapping](https://mlsanity.com/paper/2209.13274/) (2022) - [ALIKE: Accurate and Lightweight Keypoint Detection and Descriptor Extraction](https://mlsanity.com/paper/2112.02906/) (2021) - [OmniGlue: Generalizable Feature Matching with Foundation Model Guidance](https://mlsanity.com/paper/2405.12979/) (2024) - [SiLK -- Simple Learned Keypoints](https://mlsanity.com/paper/2304.06194/) (2023) - [RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration](https://mlsanity.com/paper/2303.12384/) (2023) - [NeRF-Loc: Visual Localization with Conditional Neural Radiance Field](https://mlsanity.com/paper/2304.07979/) (2023) - [Single-Image Depth Prediction Makes Feature Matching Easier](https://mlsanity.com/paper/2008.09497/) (2020) - [Continual Learning for Image-Based Camera Localization](https://mlsanity.com/paper/2108.09112/) (2021) - [Onboard dynamic-object detection and tracking for autonomous robot navigation with RGB-D camera](https://mlsanity.com/paper/2303.00132/) (2023) - [3DG-STFM: 3D Geometric Guided Student-Teacher Feature Matching](https://mlsanity.com/paper/2207.02375/) (2022) - [FeatureBooster: Boosting Feature Descriptors with a Lightweight Neural Network](https://mlsanity.com/paper/2211.15069/) (2022) - [LFM-3D: Learnable Feature Matching Across Wide Baselines Using 3D Signals](https://mlsanity.com/paper/2303.12779/) (2023) - [ObVi-SLAM: Long-Term Object-Visual SLAM](https://mlsanity.com/paper/2309.15268/) (2023) - [iSimLoc: Visual Global Localization for Previously Unseen Environments with Simulated Images](https://mlsanity.com/paper/2209.06376/) (2022) - [Progressive Retinal Image Registration via Global and Local Deformable Transformations](https://mlsanity.com/paper/2409.01068/) (2024) ## Built on by (most cited first, 12 of 12) - [Deep Learning Reforms Image Matching: A Survey and Outlook](https://mlsanity.com/paper/2506.04619/) (2025) - [DistillMatch: Leveraging Knowledge Distillation from Vision Foundation Model for Multimodal Image Matching](https://mlsanity.com/paper/2509.16017/) (2025) - [SURE: Semi-dense Uncertainty-REfined Feature Matching](https://mlsanity.com/paper/2603.04869/) (2026) - [GESS: Multi-cue Guided Local Feature Learning via Geometric and Semantic Synergy](https://mlsanity.com/paper/2604.05359/) (2026) - [OrthoTrack: Continuous 6-DoF UAV Trajectory Estimation Anchored in Public Orthophotos](https://mlsanity.com/paper/2606.25245/) (2026) - [Coarse-to-Fine Non-Rigid Registration for Side-Scan Sonar Mosaicking](https://mlsanity.com/paper/2512.00052/) (2025) - [From Pairs to Sequences: Track-Aware Policy Gradients for Keypoint Detection](https://mlsanity.com/paper/2602.20630/) (2026) - [REDI-Match: Rotation-Equivariant Distillation for Efficient and Robust Dense Matching](https://mlsanity.com/paper/2606.24330/) (2026) - [MuViSeg: Multi-View Segment Correspondences from Dense Geometry Priors](https://mlsanity.com/paper/2607.17938/) (2026) - [Real-Time Visual Obstruction Detection in Surgical Augmented Reality](https://mlsanity.com/paper/2608.00232/) (2026) - [Cross-View Feature Matching: Survey, Benchmarking, and Foundation-Model Perspectives](https://mlsanity.com/paper/2608.11093/) (2026) - [DECO: Depth-Guided Co-Visibility Reasoning for Low-Altitude UAV Visual Localization](https://mlsanity.com/paper/2608.22289/) (2026) ## Abstract (arXiv) Robust and efficient local feature matching plays a crucial role in applications such as SLAM and visual localization for robotics. Despite great progress, it is still very challenging to extract robust and discriminative visual features in scenarios with drastic lighting changes, low texture areas, or repetitive patterns. In this paper, we propose a new lightweight network called textitLiftFeat, which lifts the robustness of raw descriptor by aggregating 3D geometric feature. Specifically, we first adopt a pre-trained monocular depth estimation model to generate pseudo surface normal label, supervising the extraction of 3D geometric feature in terms of predicted surface normal. We then design a 3D geometry-aware feature lifting module to fuse surface normal feature with raw 2D descriptor feature. Integrating such 3D geometric feature enhances the discriminative ability of 2D feature description in extreme conditions. Extensive experimental results on relative pose estimation, homography estimation, and visual localization tasks, demonstrate that our LiftFeat outperforms some lightweight state-of-the-art methods. Code will be released at : https://github.com/lyp-deeplearning/LiftFeat.