mlsanityData to 7 Oct 2026

Graph-CoVis: GNN-based Multi-view Panorama Global Pose Estimation

arXiv 2304.13201 ↗First posted 26 Apr 2023cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

In this paper, we address the problem of wide-baseline camera pose estimation from a group of 360^circ panoramas under upright-camera assumption. Recent work has demonstrated the merit of deep-learning for end-to-end direct relative pose regression in 360^circ panorama pairs [11]. To exploit the benefits of multi-view logic in a learning-based framework, we introduce Graph-CoVis, which non-trivially extends CoVisPose [11] from relative two-view to global multi-view spherical camera pose estimation. Graph-CoVis is a novel Graph Neural Network based architecture that jointly learns the co-visible structure and global motion in an end-to-end and fully-supervised approach. Using the ZInD [4] dataset, which features real homes presenting wide-baselines, occlusion, and limited visual overlap, we show that our model performs competitively to state-of-the-art approaches.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 12 of its 32 references that are in the map. First posted on arXiv 26 Apr 2023.

Builds on

12 of 32 references.

References · 12

  1. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,437
  2. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  3. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 974
  4. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 324
  5. 2016LIFT: Learned Invariant Feature Transformcited by 305
  6. 2016DSAC - Differentiable RANSAC for Camera Localizationcited by 264
  7. 2021COTR: Correspondence Transformer for Matching Across Imagescited by 182
  8. 2021Wide-Baseline Relative Camera Pose Estimation with Directional Learningcited by 49
  9. 2022DiffPoseNet: Direct Differentiable Camera Pose Estimationcited by 27
  10. 2022Leveraging Equivariant Features for Absolute Pose Regressioncited by 17
  11. 2022PSMNet: Position-aware Stereo Merging Network for Room Layout Estimationcited by 10
  12. 2018RegNet: Learning the Optimization of Direct Image-to-Image Pose Registrationcited by 3

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 3; 2025: 3.

8 papers.

  1. 2025EDM: Equirectangular Projection-Oriented Dense Kernelized Feature Matchingcited by 7
  2. 2023Automated Camera Calibration via Homography Estimation with GNNscited by 6
  3. 2023Fingerspelling PoseNet: Enhancing Fingerspelling Translation with Pose-Based Transformer Modelscited by 5
  4. 2024Self-training Room Layout Estimation via Geometry-aware Ray-castingcited by 3
  5. 2024Structured Spatial Reasoning with Open Vocabulary Object Detectorscited by 2
  6. 2025BADGR: Bundle Adjustment Diffusion Conditioned by GRadients for Wide-Baseline Floor Plan Reconstructioncited by 1
  7. 2025Policies over Poses: Reinforcement Learning based Distributed Pose-Graph Optimization for Multi-Robot SLAMcited by 1
  8. 2024SES: Bridging the Gap Between Explainability and Prediction of Graph Neural Networkscited by 0