# Single-Image Depth Prediction Makes Feature Matching Easier

arXiv: https://arxiv.org/abs/2008.09497 · HTML: https://mlsanity.com/paper/2008.09497/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2020.

## Built on by (most cited first, 21 of 21)

- [Grounding Image Matching in 3D with MASt3R](https://mlsanity.com/paper/2406.09756/) (2024)
- [Map-free Visual Relocalization: Metric Pose Relative to a Single Image](https://mlsanity.com/paper/2210.05494/) (2022)
- [Where is your place, Visual Place Recognition?](https://mlsanity.com/paper/2103.06443/) (2021)
- [Dens3R: A Foundation Model for 3D Geometry Prediction](https://mlsanity.com/paper/2507.16290/) (2025)
- [A case for using rotation invariant features in state of the art feature matchers](https://mlsanity.com/paper/2204.10144/) (2022)
- [NinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learning](https://mlsanity.com/paper/2112.12785/) (2021)
- [Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTV](https://mlsanity.com/paper/2307.10713/) (2023)
- [RoRD: Rotation-Robust Descriptors and Orthographic Views for Local Feature Matching](https://mlsanity.com/paper/2103.08573/) (2021)
- [CrowdDriven: A New Challenging Dataset for Outdoor Visual Localization](https://mlsanity.com/paper/2109.04527/) (2021)
- [ScaleNet: A Shallow Architecture for Scale Estimation](https://mlsanity.com/paper/2112.04846/) (2021)
- [LiftFeat: 3D Geometry-Aware Local Feature Matching](https://mlsanity.com/paper/2505.03422/) (2025)
- [LFM-3D: Learnable Feature Matching Across Wide Baselines Using 3D Signals](https://mlsanity.com/paper/2303.12779/) (2023)
- [Structured Epipolar Matcher for Local Feature Matching](https://mlsanity.com/paper/2303.16646/) (2023)
- [Kick Back & Relax++: Scaling Beyond Ground-Truth Depth with SlowTV & CribsTV](https://mlsanity.com/paper/2403.01569/) (2024)
- [Deep Learning Reforms Image Matching: A Survey and Outlook](https://mlsanity.com/paper/2506.04619/) (2025)
- [Image Matching Filtering and Refinement by Planes and Beyond](https://mlsanity.com/paper/2411.09484/) (2024)
- [Learned Two-Plane Perspective Prior based Image Resampling for Efficient Object Detection](https://mlsanity.com/paper/2303.14311/) (2023)
- [Sparse-to-Complete: From Sparse Image Captures to Complete 3D Scenes](https://mlsanity.com/paper/2605.05664/) (2026)
- [Matching with AffNet based rectifications](https://mlsanity.com/paper/2207.14660/) (2022)
- [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)

Good local features improve the robustness of many 3D re-localization and multi-view reconstruction pipelines. The problem is that viewing angle and distance severely impact the recognizability of a local feature. Attempts to improve appearance invariance by choosing better local feature points or by leveraging outside information, have come with pre-requisites that made some of them impractical. In this paper, we propose a surprisingly effective enhancement to local feature extraction, which improves matching. We show that CNN-based depths inferred from single RGB images are quite helpful, despite their flaws. They allow us to pre-warp images and rectify perspective distortions, to significantly enhance SIFT and BRISK features, enabling more good matches, even when cameras are looking at the same scene but in opposite directions.