mlsanityData to 7 Oct 2026

NinjaDesc: Content-Concealing Visual Descriptors via Adversarial Learning

arXiv 2112.12785 ↗First posted 23 Dec 2021cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

In the light of recent analyses on privacy-concerning scene revelation from visual descriptors, we develop descriptors that conceal the input image content. In particular, we propose an adversarial learning framework for training visual descriptors that prevent image reconstruction, while maintaining the matching accuracy. We let a feature encoding network and image reconstruction network compete with each other, such that the feature encoder tries to impede the image reconstruction with its generated descriptors, while the reconstructor tries to recover the input image from the descriptors. The experimental results demonstrate that the visual descriptors obtained with our method significantly deteriorate the image reconstruction quality with minimal impact on correspondence matching and camera localization performance.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 42 of its 89 references that are in the map. First posted on arXiv 23 Dec 2021.

Builds on

42 of 89 references.

References · 42

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  5. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  6. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  7. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  8. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  9. 2015NetVLAD: CNN architecture for weakly supervised place recognitioncited by 935
  10. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 801
  11. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  12. 2014Understanding Deep Image Representations by Inverting Themcited by 399
30 more
  1. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 261
  2. 2019Kornia: an Open Source Differentiable Computer Vision Library for PyTorchcited by 231
  3. 2020Image Matching across Wide Baselines: From Paper to Practicecited by 224
  4. 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
  5. 2019R2D2: Repeatable and Reliable Detector and Descriptorcited by 206
  6. 2019Learning with Average Precision: Training Image Retrieval with a Listwise Losscited by 184
  7. 2015Inverting Visual Representations with Convolutional Networkscited by 168
  8. 2019SOSNet: Second Order Similarity Regularization for Local Descriptor Learningcited by 131
  9. 2017Controllable Invariance through Adversarial Feature Learningcited by 127
  10. 2020The DeepFake Detection Challenge (DFDC) Datasetcited by 125
  11. 2019Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filterscited by 117
  12. 2019ContextDesc: Local Descriptor Augmentation with Cross-Modality Contextcited by 79
  13. 2019Revealing Scenes by Inverting Structure from Motion Reconstructionscited by 66
  14. 2020Robust Image Retrieval-based Visual Localization using Kapturecited by 66
  15. 2020Learning and aggregating deep local descriptors for instance-level recognitioncited by 54
  16. 2019Mitigating Information Leakage in Image Representations: A Maximum Entropy Approachcited by 48
  17. 2019Privacy Preserving Image-Based Localizationcited by 47
  18. 2020SOLAR: Second-Order Loss and Attention for Image Retrievalcited by 45
  19. 2019Local Features and Visual Words Emerge in Activationscited by 36
  20. 2019Adversarial Learning of Privacy-Preserving and Task-Oriented Representationscited by 35
  21. 2018Learning Privacy Preserving Encodings through Adversarial Trainingcited by 30
  22. 2018Adversarial Training for Adverse Conditions: Robust Metric Localisation using Appearance Transfercited by 25
  23. 2020Single-Image Depth Prediction Makes Feature Matching Easiercited by 21
  24. 2021How Privacy-Preserving are Line Clouds? Recovering Scene Details from 3D Linescited by 19
  25. 2020Privacy Preserving Visual SLAMcited by 15
  26. 2017Privacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryptioncited by 14
  27. 2021Analysis and Mitigations of Reverse Engineering Attacks on Local Feature Descriptorscited by 10
  28. 2015Image Reconstruction from Bag-of-Visual-Wordscited by 6
  29. 2020Privacy-Preserving Image Features via Adversarial Affine Subspace Embeddingscited by 4
  30. 2020Domain Adaptation of Learned Features for Visual Localizationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 9; 2024: 2; 2025: 1; 2026: 6.

21 papers.

Sort:

By area:

  1. 2023OrienterNet: Visual Localization in 2D Public Maps with Neural Matchingcited by 84
  2. 2023An Outlook into the Future of Egocentric Visioncited by 84
  3. 2022Is Geometry Enough for Matching in Visual Localization?cited by 48
  4. 2023SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understandingcited by 38
  5. 2023DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matchingcited by 17
  6. 2023LDP-Feat: Image Features with Local Differential Privacycited by 10
  7. 2023Searching from Area to Point: A Hierarchical Framework for Semantic-Geometric Combined Feature Matchingcited by 9
  8. 2023PATROL: Privacy-Oriented Pruning for Collaborative Inference Against Model Inversion Attackscited by 9
  9. 2022Improving Feature-based Visual Localization by Geometry-Aided Matchingcited by 8
  10. 2023Privacy-Preserving Representations are not Enough -- Recovering Scene Content from Camera Posescited by 7
  11. 2022Privacy-Preserving Visual Localization with Event Camerascited by 6
  12. 2024Obfuscation Based Privacy Preserving Representations are Recoverable Using Neighborhood Informationcited by 6
9 more
  1. 2024DecentNeRFs: Decentralized Neural Radiance Fields from Crowdsourced Imagescited by 4
  2. 2023LDL: Line Distance Functions for Panoramic Localizationcited by 3
  3. 2026Privacy-Concealing Cooperative Perception for BEV Scene Segmentationcited by 2
  4. 2025ConcreTizer: Model Inversion Attack via Occupancy Classification and Dispersion Control for 3D Point Cloud Restorationcited by 1
  5. 2026Privacy-Preserving Structureless Visual Localization via Image Obfuscationcited by 0
  6. 2026Revisiting Geometric Obfuscation with Dual Convergent Lines for Privacy-Preserving Image Queries in Visual Localizationcited by 0
  7. 2026Seeing Through the Weights: Privacy Leakage in Scene Coordinate Regressioncited by 0
  8. 2026TrustCLIP: Learning Private Visual Features via Adversarial Reconstructioncited by 0
  9. 2026Misanthrope: A Privacy-Preserving Keypoint Detectorcited by 0