# Predicting Visual Overlap of Images Through Interpretable Non-Metric Box Embeddings

arXiv: https://arxiv.org/abs/2008.05785 · HTML: https://mlsanity.com/paper/2008.05785/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Aug 2020.

## Built on by (most cited first, 16 of 16)

- [Map-free Visual Relocalization: Metric Pose Relative to a Single Image](https://mlsanity.com/paper/2210.05494/) (2022)
- [LaMAR: Benchmarking Localization and Mapping for Augmented Reality](https://mlsanity.com/paper/2210.10770/) (2022)
- [Where is your place, Visual Place Recognition?](https://mlsanity.com/paper/2103.06443/) (2021)
- [Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer](https://mlsanity.com/paper/2404.14351/) (2024)
- [Viewpoint Invariant Dense Matching for Visual Geolocalization](https://mlsanity.com/paper/2109.09827/) (2021)
- [Guide Local Feature Matching by Overlap Estimation](https://mlsanity.com/paper/2202.09050/) (2022)
- [SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization](https://mlsanity.com/paper/2508.17972/) (2025)
- [R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization](https://mlsanity.com/paper/2501.01421/) (2025)
- [ScaleNet: A Shallow Architecture for Scale Estimation](https://mlsanity.com/paper/2112.04846/) (2021)
- [Representing Spatial Trajectories as Distributions](https://mlsanity.com/paper/2210.01322/) (2022)
- [Co-VisiON: Co-Visibility ReasONing on Sparse Image Sets of Indoor Scenes](https://mlsanity.com/paper/2506.16805/) (2025)
- [Scale-Net: Learning to Reduce Scale Differences for Large-Scale Invariant Image Matching](https://mlsanity.com/paper/2112.10485/) (2021)
- [Set2Box: Similarity Preserving Representation Learning of Sets](https://mlsanity.com/paper/2210.03282/) (2022)
- [Insert or Attach: Taxonomy Completion via Box Embedding](https://mlsanity.com/paper/2305.11004/) (2023)
- [YOWO: You Only Walk Once to Jointly Map An Indoor Scene and Register Ceiling-mounted Cameras](https://mlsanity.com/paper/2511.16521/) (2025)
- [Robust Scene Coordinate Regression via Geometrically-Consistent Global Descriptors](https://mlsanity.com/paper/2512.17226/) (2025)

## Abstract (arXiv)

To what extent are two images picturing the same 3D surfaces? Even when this is a known scene, the answer typically requires an expensive search across scale space, with matching and geometric verification of large sets of local features. This expense is further multiplied when a query image is evaluated against a gallery, e.g. in visual relocalization. While we don't obviate the need for geometric verification, we propose an interpretable image-embedding that cuts the search in scale space to essentially a lookup. Our approach measures the asymmetric relation between two images. The model then learns a scene-specific measure of similarity, from training examples with known 3D visible-surface overlaps. The result is that we can quickly identify, for example, which test image is a close-up version of another, and by what scale factor. Subsequently, local features need only be detected at that scale. We validate our scene-specific model by showing how this embedding yields competitive image-matching results, while being simpler, faster, and also interpretable by humans.