mlsanityData to 14 Oct 2026

Inside Out Visual Place Recognition

arXiv 2111.13546 ↗First posted 26 Nov 2021cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Visual Place Recognition (VPR) is generally concerned with localizing outdoor images. However, localizing indoor scenes that contain part of an outdoor scene can be of large value for a wide range of applications. In this paper, we introduce Inside Out Visual Place Recognition (IOVPR), a task aiming to localize images based on outdoor scenes visible through windows. For this task we present the new large-scale dataset Amsterdam-XXXL, with images taken in Amsterdam, that consists of 6.4 million panoramic street-view images and 1000 user-generated indoor queries. Additionally, we introduce a new training protocol Inside Out Data Augmentation to adapt Visual Place Recognition methods for localizing indoor images, demonstrating the potential of Inside Out Visual Place Recognition. We empirically show the benefits of our proposed data augmentation scheme on a smaller scale, whilst demonstrating the difficulty of this large-scale dataset for existing methods. With this new task we aim to encourage development of methods for IOVPR. The dataset and code are available for research purposes at https://github.com/saibr/IOVPR

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 16 of its 35 references that are in the map. First posted on arXiv 26 Nov 2021.

Builds on

16 of 35 references.

References · 16

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2018Unified Perceptual Parsing for Scene Understandingcited by 1,271
  4. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 988
  5. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 941
  6. 2020Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrievalcited by 309
  7. 2016Large-Scale Image Retrieval with Attentive Deep Local Featurescited by 238
  8. 2021Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognitioncited by 238
  9. 2018Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarkingcited by 191
  10. 2015Wide-Area Image Geolocalization with Aerial Reference Imagerycited by 186
  11. 2020Self-supervising Fine-grained Region Similarities for Large-scale Image Localizationcited by 110
  12. 2016Localizing and Orienting Street Views Using Overhead Imagerycited by 94
4 more
  1. 2019Scalable Place Recognition Under Appearance Change for Autonomous Drivingcited by 42
  2. 2019Hotels-50K: A Global Hotel Recognition Datasetcited by 13
  3. 2020Unifying Deep Local and Global Features for Image Searchcited by 12
  4. 2019Attention-Aware Age-Agnostic Visual Place Recognitioncited by 10

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 4; 2024: 5; 2025: 2.

12 papers.

  1. 2022Rethinking Visual Geo-localization for Large-Scale Applicationscited by 163
  2. 2023EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognitioncited by 111
  3. 2023Visual Place Recognition: A Tutorialcited by 31
  4. 2024SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphscited by 29
  5. 2023Are Local Features All You Need for Cross-Domain Visual Place Recognition?cited by 21
  6. 2024Revisit Anything: Visual Place Recognition via Image Segment Retrievalcited by 19
  7. 2024Swarm Intelligence in Geo-Localization: A Multi-Agent Large Vision-Language Model Collaborative Frameworkcited by 11
  8. 2025EMPLACE: Self-Supervised Urban Scene Change Detectioncited by 7
  9. 2024ProGEO: Generating Prompts through Image-Text Contrastive Learning for Visual Geo-localizationcited by 6
  10. 2024Breaking the Frame: Visual Place Recognition by Overlap Predictioncited by 3
  11. 2025To Match or Not to Match: Revisiting Image Matching for Reliable Visual Place Recognitioncited by 3
  12. 2023Divide&Classify: Fine-Grained Classification for City-Wide Visual Place Recognitioncited by 2