mlsanityData to 7 Oct 2026

Visual Correspondence Hallucination

arXiv 2106.09711 ↗First posted 17 Jun 2021cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Given a pair of partially overlapping source and target images and a keypoint in the source image, the keypoint's correspondent in the target image can be either visible, occluded or outside the field of view. Local feature matching methods are only able to identify the correspondent's location when it is visible, while humans can also hallucinate its location when it is occluded or outside the field of view through geometric reasoning. In this paper, we bridge this gap by training a network to output a peaked probability distribution over the correspondent's location, regardless of this correspondent being visible, occluded, or outside the field of view. We experimentally demonstrate that this network is indeed able to hallucinate correspondences on pairs of images captured in scenes that were not seen at training-time. We also apply this network to an absolute camera pose estimation problem and find it is significantly more robust than state-of-the-art local feature matching-based competitors.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 42 of its 67 references that are in the map. First posted on arXiv 17 Jun 2021.

Builds on

42 of 67 references.

References · 42

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  4. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  5. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  6. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  7. 2020Transformers are RNNs: Fast Autoregressive Transformers with Linear Attentioncited by 1,979
  8. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  9. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  10. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  11. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
  12. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 556
30 more
  1. 2019Stand-Alone Self-Attention in Vision Modelscited by 542
  2. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 324
  3. 2020Exploring Self-attention for Image Recognitioncited by 313
  4. 2016LIFT: Learned Invariant Feature Transformcited by 305
  5. 2019On the Relationship between Self-Attention and Convolutional Layerscited by 299
  6. 2017HPatches: A benchmark and evaluation of handcrafted and learned local descriptorscited by 261
  7. 2017Working hard to know your neighbor's margins: Local descriptor learning losscited by 212
  8. 2017Learning to Find Good Correspondencescited by 176
  9. 2018Neighbourhood Consensus Networkscited by 173
  10. 2019MAGSAC++, a fast, reliable and accurate robust estimatorcited by 160
  11. 2019Learning Two-View Correspondences and Geometry Using Order-Aware Networkcited by 148
  12. 2016Deep Image Retrieval: Learning global representations for image searchcited by 147
  13. 2017Graph-Cut RANSACcited by 133
  14. 2019Neural-Guided RANSAC: Learning Where to Sample Model Hypothesescited by 129
  15. 2018MAGSAC: marginalizing sample consensuscited by 122
  16. 2020Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutionscited by 92
  17. 2020Dual-Resolution Correspondence Networkscited by 90
  18. 2016Universal Correspondence Networkcited by 82
  19. 2019ContextDesc: Local Descriptor Augmentation with Cross-Modality Contextcited by 79
  20. 2016CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examplescited by 58
  21. 2021Wide-Baseline Relative Camera Pose Estimation with Directional Learningcited by 49
  22. 2021Extreme Rotation Estimation using Dense Correlation Volumescited by 42
  23. 2021Planar Surface Reconstruction from Sparse Viewscited by 40
  24. 2020High-dimensional Convolutional Networks for Geometric Pattern Recognitioncited by 24
  25. 2018Extreme Relative Pose Estimation for RGB-D Scans via Scene Completioncited by 22
  26. 2019Extreme Relative Pose Network under Hybrid Representationscited by 19
  27. 2020Associative3D: Volumetric Reconstruction from Sparse Viewscited by 18
  28. 2021Neural Reprojection Error: Merging Feature Learning and Camera Pose Estimationcited by 17
  29. 2016PN-Net: Conjoined Triple Deep Network for Learning Local Image Descriptorscited by 16
  30. 2017Recent Advances in Features Extraction and Description Algorithms: A Comprehensive Surveycited by 8

Built on by

Cited by year

Citing papers per year: 2022: 4; 2023: 1.

5 papers.

  1. 2022Particle Video Revisited: Tracking Through Occlusions Using Point Trajectoriescited by 215
  2. 2022QuadTree Attention for Vision Transformerscited by 129
  3. 2022ObjectMatch: Robust Registration using Canonical Object Correspondencescited by 15
  4. 2022Self-supervised Learning with Local Contrastive Loss for Detection and Semantic Segmentationcited by 8
  5. 2023Structured Epipolar Matcher for Local Feature Matchingcited by 8