mlsanityData to 14 Oct 2026

RelPose++: Recovering 6D Poses from Sparse-view Observations

arXiv 2305.04926 ↗First posted 8 May 2023cs.CVcited by 87

Not on the map. Why?

Abstract (arXiv)

We address the task of estimating 6D camera poses from sparse-view image sets (2-8 images). This task is a vital pre-processing stage for nearly all contemporary (neural) reconstruction algorithms but remains challenging given sparse views, especially for objects with visual symmetries and texture-less surfaces. We build on the recent RelPose framework which learns a network that infers distributions over relative rotations over image pairs. We extend this approach in two key ways; first, we use attentional transformer layers to process multiple images jointly, since additional views of an object may resolve ambiguous symmetries in any given image pair (such as the handle of a mug that becomes visible in a third view). Second, we augment this network to also report camera translations by defining an appropriate coordinate system that decouples the ambiguity in rotation estimation from translation prediction. Our final system results in large improvements in 6D pose prediction over prior art on both seen and unseen object categories and also enables pose estimation and 3D reconstruction for in-the-wild objects.

Key facts. Cited by 87 papers in the map (data through 14 Oct 2026). Builds on 46 of its 70 references that are in the map. First posted on arXiv 8 May 2023.

Builds on

46 of 70 references.

References · 46

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  5. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  6. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  7. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  8. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 988
  9. 2017End-to-end Recovery of Human Shape and Posecited by 885
  10. 2020ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAMcited by 878
  11. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 806
  12. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 687
34 more
  1. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  2. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 642
  3. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  4. 2019MediaPipe: A Framework for Building Perception Pipelinescited by 583
  5. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 559
  6. 2019Making Convolutional Networks Shift-Invariant Againcited by 391
  7. 2018Learning 3D Human Dynamics from Videocited by 316
  8. 2022SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstructioncited by 216
  9. 2018Stereo Magnification: Learning View Synthesis using Multiplane Imagescited by 211
  10. 2020D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometrycited by 206
  11. 2017DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networkscited by 175
  12. 2020Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotationscited by 155
  13. 2020Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wildcited by 152
  14. 2021NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wildcited by 136
  15. 2017VNect: Real-time 3D Human Pose Estimation with a Single RGB Cameracited by 129
  16. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  17. 2016Universal Correspondence Networkcited by 82
  18. 2018Explaining the Ambiguity of Object Detection and 6D Pose From Visual Datacited by 68
  19. 2021Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifoldcited by 65
  20. 2022SparsePose: Sparse-View Camera Pose Regression and Refinementcited by 53
  21. 2022Few-View Object Reconstruction with Unknown Categories and Camera Posescited by 53
  22. 2021Wide-Baseline Relative Camera Pose Estimation with Directional Learningcited by 49
  23. 2017Relative Camera Pose Estimation Using Convolutional Neural Networkscited by 47
  24. 2021Extreme Rotation Estimation using Dense Correlation Volumescited by 42
  25. 2021NeMo: Neural Mesh Models of Contrastive Features for Robust 3D Pose Estimationcited by 41
  26. 2019Pose from Shape: Deep Pose Estimation for Arbitrary 3D Objectscited by 39
  27. 2022The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTscited by 38
  28. 2017SegICP: Integrated Deep Semantic Segmentation and Pose Estimationcited by 29
  29. 2017Learning 3D Object Categories by Looking Around Themcited by 26
  30. 2022Virtual Correspondence: Humans as a Cue for Extreme-View Geometrycited by 25
  31. 2021PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learningcited by 19
  32. 2020Learning Orientation Distributions for Object Pose Estimationcited by 18
  33. 2022PIZZA: A Powerful Image-only Zero-Shot Zero-CAD Approach to 6 DoF Trackingcited by 15
  34. 2021MetaPose: Fast 3D Pose from Multiple Views without 3D Supervisioncited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 11; 2024: 32; 2025: 31; 2026: 13.

87 papers.

Sort:

By area:

  1. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  2. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  3. 2025Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Passcited by 367
  4. 2023Visual Geometry Grounded Deep Structure From Motioncited by 227
  5. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 180
  6. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  7. 2024MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motioncited by 162
  8. 2023PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustmentcited by 147
  9. 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 131
  10. 2024RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videoscited by 115
  11. 2025SpatialTrackerV2: 3D Point Tracking Made Easycited by 87
  12. 2024Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localizationcited by 82
38 more
  1. 2024Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizercited by 73
  2. 2025Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priorscited by 72
  3. 2023LEAP: Liberate Sparse-view 3D Modeling from Camera Posescited by 65
  4. 2025Light3R-SfM: Towards Feed-forward Structure-from-Motioncited by 47
  5. 2025Matrix3D: Large Photogrammetry Model All-in-Onecited by 40
  6. 2025No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Viewscited by 40
  7. 2025AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesiscited by 39
  8. 2024SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Viewscited by 35
  9. 2024SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesiscited by 34
  10. 2024Reconstructing People, Places, and Camerascited by 31
  11. 2023Open-vocabulary object 6D pose estimationcited by 29
  12. 2025E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-trainingcited by 22
  13. 2023ZeroPose: CAD-Prompted Zero-shot Object 6D Pose Estimation in Cluttered Scenescited by 20
  14. 2025SAIL-Recon: Large SfM by Augmenting Scene Regression with Localizationcited by 20
  15. 2025One2Any: One-Reference 6D Pose Estimation for Any Objectcited by 18
  16. 2023UpFusion: Novel View Diffusion from Unposed Sparse View Observationscited by 14
  17. 2023iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse Viewscited by 14
  18. 2025DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusioncited by 14
  19. 2024FAR: Flexible, Accurate and Robust 6DoF Relative Camera Pose Estimationcited by 12
  20. 2024UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Imagecited by 12
  21. 20233D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimationcited by 11
  22. 2024High-resolution open-vocabulary object 6D pose estimationcited by 10
  23. 2024Generic Objects as Pose Probes for Few-shot View Synthesiscited by 9
  24. 2024Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesiscited by 9
  25. 2023ID-Pose: Sparse-view Camera Pose Estimation by Inverting Diffusion Modelscited by 8
  26. 2025Stereo-GS: Multi-View Stereo Vision Model for Generalizable 3D Gaussian Splatting Reconstructioncited by 8
  27. 2024Pose-Aware Self-Supervised Learning with Viewpoint Trajectory Regularizationcited by 7
  28. 2024Can Generative Video Models Help Pose Estimation?cited by 7
  29. 2025SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Viewscited by 7
  30. 2024Extreme Rotation Estimation in the Wildcited by 6
  31. 2025SAB3R: Semantic-Augmented Backbone in 3D Reconstructioncited by 6
  32. 2025Emergent Extreme-View Geometry in 3D Foundation Modelscited by 6
  33. 2024The More You See in 2D, the More You Perceive in 3Dcited by 5
  34. 2024SRPose: Two-view Relative Pose Estimation with Sparse Keypointscited by 5
  35. 2025Reloc-VGGT: Visual Re-localization with Geometry Grounded Transformercited by 5
  36. 2026Video Understanding: From Geometry and Semantics to Unified Modelscited by 5
  37. 2024Extreme Two-View Geometry From Object Poses with Diffusion Modelscited by 4
  38. 2024Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Predictioncited by 4

50 most cited of 87 All 87 (JSON)