mlsanityData to 14 Oct 2026

Extreme Rotation Estimation in the Wild

arXiv 2411.07096 ↗First posted 11 Nov 2024cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

We present a technique and benchmark dataset for estimating the relative 3D orientation between a pair of Internet images captured in an extreme setting, where the images have limited or non-overlapping field of views. Prior work targeting extreme rotation estimation assume constrained 3D environments and emulate perspective images by cropping regions from panoramic views. However, real images captured in the wild are highly diverse, exhibiting variation in both appearance and camera intrinsics. In this work, we propose a Transformer-based method for estimating relative rotations in extreme real-world settings, and contribute the ExtremeLandmarkPairs dataset, assembled from scene-level Internet photo collections. Our evaluation demonstrates that our approach succeeds in estimating the relative rotations in a wide variety of extreme-view Internet image pairs, outperforming various baselines, including dedicated rotation estimation techniques and contemporary 3D reconstruction methods.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 40 of its 56 references that are in the map. First posted on arXiv 11 Nov 2024.

Builds on

40 of 56 references.

References · 40

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  4. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,611
  5. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  6. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  7. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  8. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  9. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  10. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  11. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  12. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
28 more
  1. 2023LightGlue: Local Feature Matching at Light Speedcited by 590
  2. 2020DISK: Learning local features with policy gradientcited by 312
  3. 2016DSAC - Differentiable RANSAC for Camera Localizationcited by 266
  4. 2021Back to the Feature: Learning Robust Camera Localization from Pixels to Posecited by 199
  5. 2022DKM: Dense Kernelized Feature Matching for Geometry Estimationcited by 177
  6. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  7. 2022CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completioncited by 160
  8. 2017A Survey of Structure from Motioncited by 158
  9. 2023PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustmentcited by 147
  10. 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 131
  11. 2020Learning Feature Descriptors using Camera Pose Supervisioncited by 104
  12. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  13. 2023RelPose++: Recovering 6D Poses from Sparse-view Observationscited by 87
  14. 2022Perspective Fields for Single Image Camera Calibrationcited by 75
  15. 2023DeDoDe: Detect, Don't Describe -- Describe, Don't Detect for Local Feature Matchingcited by 63
  16. 2024MegaScenes: Scene-Level View Synthesis at Scalecited by 58
  17. 2022SparsePose: Sparse-View Camera Pose Regression and Refinementcited by 53
  18. 2021Multi-view 3D Reconstruction with Transformercited by 52
  19. 2021Wide-Baseline Relative Camera Pose Estimation with Directional Learningcited by 49
  20. 2019The StreetLearn Environment and Datasetcited by 42
  21. 2021Extreme Rotation Estimation using Dense Correlation Volumescited by 42
  22. 2022The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTscited by 38
  23. 2023Doppelgangers: Learning to Disambiguate Images of Similar Structurescited by 32
  24. 2023POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Referencecited by 30
  25. 2022PlaneFormers: From Sparse View Planes to 3D Reconstructioncited by 26
  26. 2018Extreme Relative Pose Estimation for RGB-D Scans via Scene Completioncited by 22
  27. 2019Extreme Relative Pose Network under Hybrid Representationscited by 19
  28. 2022FvOR: Robust Joint Shape and Pose Optimization for Few-view Object Reconstructioncited by 19

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 1.

6 papers.

  1. 2025Beyond the Frame: Generating 360 Panoramic Videos from Perspective Videoscited by 16
  2. 2024Can Generative Video Models Help Pose Estimation?cited by 7
  3. 2025Deep Learning Reforms Image Matching: A Survey and Outlookcited by 7
  4. 2025Emergent Extreme-View Geometry in 3D Foundation Modelscited by 6
  5. 2026Long-tail Internet photo reconstructioncited by 4
  6. 2025PoseCrafter: Extreme Pose Estimation with Hybrid Video Synthesiscited by 1