# Multi-View Optimization of Local Feature Geometry

arXiv: https://arxiv.org/abs/2003.08348 · HTML: https://mlsanity.com/paper/2003.08348/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Mar 2020.

## Built on by (most cited first, 24 of 24)

- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [Visual Geometry Grounded Deep Structure From Motion](https://mlsanity.com/paper/2312.04563/) (2023)
- [Pixel-Perfect Structure-from-Motion with Featuremetric Refinement](https://mlsanity.com/paper/2108.08291/) (2021)
- [Deep Patch Visual Odometry](https://mlsanity.com/paper/2208.04726/) (2022)
- [OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models](https://mlsanity.com/paper/2301.07673/) (2023)
- [RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild](https://mlsanity.com/paper/2208.05963/) (2022)
- [Detector-Free Structure from Motion](https://mlsanity.com/paper/2306.15669/) (2023)
- [3D Line Mapping Revisited](https://mlsanity.com/paper/2303.17504/) (2023)
- [Robust Incremental Structure-from-Motion with Hybrid Features](https://mlsanity.com/paper/2409.19811/) (2024)
- [MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion](https://mlsanity.com/paper/2504.20040/) (2025)
- [Dense-SfM: Structure from Motion with Dense Consistent Matching](https://mlsanity.com/paper/2501.14277/) (2025)
- [ScaleNet: A Shallow Architecture for Scale Estimation](https://mlsanity.com/paper/2112.04846/) (2021)
- [TrackNeRF: Bundle Adjusting NeRF from Sparse and Noisy Views via Feature Tracks](https://mlsanity.com/paper/2408.10739/) (2024)
- [FeatureBooster: Boosting Feature Descriptors with a Lightweight Neural Network](https://mlsanity.com/paper/2211.15069/) (2022)
- [TopicFM+: Boosting Accuracy and Efficiency of Topic-Assisted Feature Matching](https://mlsanity.com/paper/2307.00485/) (2023)
- [Nerfels: Renderable Neural Codes for Improved Camera Pose Estimation](https://mlsanity.com/paper/2206.01916/) (2022)
- [3D Video Object Detection with Learnable Object-Centric Global Optimization](https://mlsanity.com/paper/2303.15416/) (2023)
- [Effect of Parameter Optimization on Classical and Learning-based Image Matching Methods](https://mlsanity.com/paper/2108.08179/) (2021)
- [DAC: Detector-Agnostic Spatial Covariances for Deep Local Features](https://mlsanity.com/paper/2305.12250/) (2023)
- [CVD-SfM: A Cross-View Deep Front-end Structure-from-Motion System for Sparse Localization in Multi-Altitude Scenes](https://mlsanity.com/paper/2508.01936/) (2025)
- [Consensus Learning with Deep Sets for Essential Matrix Estimation](https://mlsanity.com/paper/2406.17414/) (2024)
- [Fixing the RANSAC Stopping Criterion](https://mlsanity.com/paper/2503.07829/) (2025)
- [XRefine: Attention-Guided Keypoint Match Refinement](https://mlsanity.com/paper/2601.12530/) (2026)
- [Unified and Efficient Point-Line Local Features](https://mlsanity.com/paper/2608.19894/) (2026)

## Abstract (arXiv)

In this work, we address the problem of refining the geometry of local image features from multiple views without known scene or camera geometry. Current approaches to local feature detection are inherently limited in their keypoint localization accuracy because they only operate on a single view. This limitation has a negative impact on downstream tasks such as Structure-from-Motion, where inaccurate keypoints lead to large errors in triangulation and camera localization. Our proposed method naturally complements the traditional feature extraction and matching paradigm. We first estimate local geometric transformations between tentative matches and then optimize the keypoint locations over multiple views jointly according to a non-linear least squares formulation. Throughout a variety of experiments, we show that our method consistently improves the triangulation and camera localization performance for both hand-crafted and learned local features.