mlsanityData to 7 Oct 2026

Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency

arXiv 2402.09237 ↗First posted 14 Feb 2024cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

State-of-the-art visual localization approaches generally rely on a first image retrieval step whose role is crucial. Yet, retrieval often struggles when facing varying conditions, due to e.g. weather or time of day, with dramatic consequences on the visual localization accuracy. In this paper, we improve this retrieval step and tailor it to the final localization task. Among the several changes we advocate for, we propose to synthesize variants of the training set images, obtained from generative text-to-image models, in order to automatically expand the training set towards a number of nameable variations that particularly hurt visual localization. After expanding the training set, we propose a training approach that leverages the specificities and the underlying geometry of this mix of real and synthetic images. We experimentally show that those changes translate into large improvements for the most challenging visual localization datasets. Project page: https://europe.naverlabs.com/ret4loc

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 89 of its 130 references that are in the map. First posted on arXiv 14 Feb 2024.

Builds on

89 of 130 references.

References · 89

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  7. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  8. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  9. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  10. 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
  11. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  12. 2017Billion-scale similarity search with GPUscited by 2,477
38 more
  1. 2021Learning to Prompt for Vision-Language Modelscited by 2,269
  2. 2017Arbitrary Style Transfer in Real-time with Adaptive Instance Normalizationcited by 1,998
  3. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  4. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  5. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,366
  6. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  7. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Modelscited by 1,168
  8. 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
  9. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 935
  10. 2019AugMix: A Simple Data Processing Method to Improve Robustness and Uncertaintycited by 897
  11. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  12. 2017Unsupervised Image-to-Image Translation Networkscited by 602
  13. 2023LightGlue: Local Feature Matching at Light Speedcited by 583
  14. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 556
  15. 2023Zero-shot Image-to-Image Translationcited by 503
  16. 2017Fine-tuning CNN Image Retrieval with No Human Annotationcited by 497
  17. 2017Semantic Foggy Scene Understanding with Synthetic Datacited by 401
  18. 2016Virtual Worlds as Proxy for Multi-Object Tracking Analysiscited by 340
  19. 2023Synthetic Data from Diffusion Models Improves ImageNet Classificationcited by 326
  20. 2022Is synthetic data from generative models ready for image recognition?cited by 320
  21. 2016DehazeNet: An End-to-End System for Single Image Haze Removalcited by 313
  22. 2019Bidirectional Learning for Domain Adaptation of Semantic Segmentationcited by 308
  23. 2023Effective Data Augmentation With Diffusion Modelscited by 282
  24. 2016Large-Scale Image Retrieval with Attentive Deep Local Featurescited by 238
  25. 2021Patch-NetVLAD: Multi-Scale Fusion of Locally-Global Descriptors for Place Recognitioncited by 236
  26. 2017Attentive Generative Adversarial Network for Raindrop Removal from a Single Imagecited by 204
  27. 2023UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wildcited by 197
  28. 2019Learning with Average Precision: Training Image Retrieval with a Listwise Losscited by 184
  29. 2019Understanding the Limitations of CNN-based Absolute Camera Pose Regressioncited by 177
  30. 2020Visual Camera Re-Localization from RGB and RGB-D Images Using DSACcited by 176
  31. 2022Fake it till you make it: Learning transferable representations from synthetic ImageNet clonescited by 171
  32. 2018Densely Connected Pyramid Dehazing Networkcited by 145
  33. 2018A Closed-form Solution to Photorealistic Image Stylizationcited by 133
  34. 2018Gated Fusion Network for Single Image Dehazingcited by 133
  35. 2019Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentationcited by 126
  36. 2022TransVPR: Transformer-based place recognition with multi-level attention aggregationcited by 102
  37. 2018DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptationcited by 101
  38. 2023Diversify Your Vision Datasets with Automatic Diffusion-Based Augmentationcited by 100

50 most cited of 89 All 89 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Instance-Level Generation for Representation Learningcited by 1