mlsanityData to 14 Oct 2026

Occ2Net: Robust Image Matching Based on 3D Occupancy Estimation for Occluded Regions

arXiv 2308.16160 ↗First posted 14 Aug 2023cs.CV eess.IVcited by 5

Not on the map. Why?

Abstract (arXiv)

Image matching is a fundamental and critical task in various visual applications, such as Simultaneous Localization and Mapping (SLAM) and image retrieval, which require accurate pose estimation. However, most existing methods ignore the occlusion relations between objects caused by camera motion and scene structure. In this paper, we propose Occ2Net, a novel image matching method that models occlusion relations using 3D occupancy and infers matching points in occluded regions. Thanks to the inductive bias encoded in the Occupancy Estimation (OE) module, it greatly simplifies bootstrapping of a multi-view consistent 3D representation that can then integrate information from multiple views. Together with an Occlusion-Aware (OA) module, it incorporates attention layers and rotation alignment to enable matching between occluded and visible points. We evaluate our method on both real-world and simulated datasets and demonstrate its superior performance over state-of-the-art methods on several metrics, especially in occlusion scenarios.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 37 of its 56 references that are in the map. First posted on arXiv 14 Aug 2023.

Builds on

37 of 56 references.

References · 37

  1. 2017Attention Is All You Needcited by 60,361
  2. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  3. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  4. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  5. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  6. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,136
  7. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 988
  8. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  9. 2020ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAMcited by 878
  10. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 806
  11. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  12. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 687
25 more
  1. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 506
  2. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 363
  3. 2020Point-GNN: Graph Neural Network for 3D Object Detection in a Point Cloudcited by 335
  4. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 326
  5. 2020DISK: Learning local features with policy gradientcited by 312
  6. 2016LIFT: Learned Invariant Feature Transformcited by 306
  7. 2022MAT: Mask-Aware Transformer for Large Hole Image Inpaintingcited by 218
  8. 2021Rethinking and Improving Relative Position Encoding for Vision Transformercited by 207
  9. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 183
  10. 2017Learning to Find Good Correspondencescited by 176
  11. 2018Neighbourhood Consensus Networkscited by 174
  12. 2022ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformercited by 171
  13. 2019Learning Two-View Correspondences and Geometry Using Order-Aware Networkcited by 149
  14. 2022QuadTree Attention for Vision Transformerscited by 129
  15. 2020Efficient Neighbourhood Consensus Networks via Submanifold Sparse Convolutionscited by 93
  16. 2020Dual-Resolution Correspondence Networkscited by 90
  17. 2021Aggregated Contextual Transformations for High-Resolution Image Inpaintingcited by 89
  18. 2023OccDepth: A Depth-Aware Method for 3D Semantic Scene Completioncited by 86
  19. 2022Incremental Transformer Structure Enhanced Image Inpainting with Masking Positional Encodingcited by 83
  20. 2019ContextDesc: Local Descriptor Augmentation with Cross-Modality Contextcited by 79
  21. 2021Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion Modelingcited by 43
  22. 2017Toward Geometric Deep SLAMcited by 38
  23. 2022Amodal Panoptic Segmentationcited by 38
  24. 2021Instance-wise Occlusion and Depth Orders in Natural Scenescited by 31
  25. 2022Image Amodal Completion: A Surveycited by 18

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 1.

5 papers.

  1. 2025Alligat0R: Pre-Training Through Co-Visibility Segmentation for Relative Camera Pose Regressioncited by 10
  2. 2025RUBIK: A Structured Benchmark for Image Matching across Geometric Challengescited by 8
  3. 2024ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypothesescited by 6
  4. 2025Geometric Visual Fusion Graph Neural Networks for Multi-Person Human-Object Interaction Recognition in Videoscited by 3
  5. 2026Revisiting Cross-View Completion: Self-Supervised Pre-Training via Reconstruction Error Comparisoncited by 1