mlsanityData to 14 Oct 2026

SparsePose: Sparse-View Camera Pose Regression and Refinement

arXiv 2211.16991 ↗First posted 29 Nov 2022cs.CVcited by 53

Not on the map. Why?

Abstract (arXiv)

Camera pose estimation is a key step in standard 3D reconstruction pipelines that operate on a dense set of images of a single object or scene. However, methods for pose estimation often fail when only a few images are available because they rely on the ability to robustly identify and match visual features between image pairs. While these methods can work robustly with dense camera views, capturing a large set of images can be time-consuming or impractical. We propose SparsePose for recovering accurate camera poses given a sparse set of wide-baseline images (fewer than 10). The method learns to regress initial camera poses and then iteratively refine them after training on a large-scale dataset of objects (Co3D: Common Objects in 3D). SparsePose significantly outperforms conventional and learning-based baselines in recovering accurate camera rotations and translations. We also demonstrate our pipeline for high-fidelity 3D reconstruction using only 5-9 images of an object.

Key facts. Cited by 53 papers in the map (data through 14 Oct 2026). Builds on 59 of its 84 references that are in the map. First posted on arXiv 29 Nov 2022.

Builds on

59 of 84 references.

References · 59

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  4. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  6. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  7. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
  8. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  9. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  10. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  11. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
  12. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 861
38 more
  1. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  2. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  3. 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
  4. 2022Block-NeRF: Scalable Large Scene Neural View Synthesiscited by 724
  5. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  6. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 642
  7. 2016Learning to learn by gradient descent by gradient descentcited by 620
  8. 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 615
  9. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 559
  10. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  11. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 382
  12. 2016LIFT: Learned Invariant Feature Transformcited by 306
  13. 2022Novel View Synthesis with Diffusion Modelscited by 300
  14. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  15. 2017A General and Adaptive Robust Loss Functioncited by 236
  16. 2021A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Posecited by 233
  17. 2021Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representationscited by 227
  18. 2020Image Matching across Wide Baselines: From Paper to Practicecited by 225
  19. 2020D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometrycited by 206
  20. 2020AutoInt: Automatic Integration for Fast Neural Volume Renderingcited by 204
  21. 2021Self-Calibrating Neural Radiance Fieldscited by 204
  22. 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 200
  23. 2021CodeNeRF: Disentangled Neural Radiance Fields for Object Categoriescited by 183
  24. 2019Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wildcited by 180
  25. 2017DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networkscited by 175
  26. 2017A Survey of Structure from Motioncited by 158
  27. 2021NeRF--: Neural Radiance Fields Without Known Camera Parameterscited by 155
  28. 2021BACON: Band-limited Coordinate Networks for Multiscale Scene Representationcited by 143
  29. 2020Self-supervised Single-view 3D Reconstruction via Semantic Consistencycited by 127
  30. 2021LASR: Learning Articulated Shape Reconstruction from a Monocular Videocited by 116
  31. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  32. 2020Shape and Viewpoint without Keypointscited by 92
  33. 2022SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collectionscited by 89
  34. 2022GARF: Gaussian Activated Radiance Fields for High Fidelity Reconstruction and Pose Estimationcited by 86
  35. 2021Unsupervised Learning of 3D Object Categories from Videos in the Wildcited by 67
  36. 2019Canonical Surface Mapping via Geometric Cycle Consistencycited by 63
  37. 2019C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motioncited by 61
  38. 2021DOVE: Learning Deformable 3D Objects by Watching Videoscited by 61

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 14; 2024: 19; 2025: 14; 2026: 6.

53 papers.

Sort:

By area:

  1. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  2. 2023Visual Geometry Grounded Deep Structure From Motioncited by 227
  3. 2025FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Viewscited by 180
  4. 2023PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Predictioncited by 165
  5. 2023PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustmentcited by 147
  6. 2024Cameras as Rays: Pose Estimation via Ray Diffusioncited by 131
  7. 2024RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videoscited by 115
  8. 2023RelPose++: Recovering 6D Poses from Sparse-view Observationscited by 87
  9. 2024Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizercited by 73
  10. 2023LEAP: Liberate Sparse-view 3D Modeling from Camera Posescited by 65
  11. 2025Matrix3D: Large Photogrammetry Model All-in-Onecited by 40
  12. 2024360-GS: Layout-guided Panoramic Gaussian Splatting For Indoor Roamingcited by 35
38 more
  1. 2024SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Viewscited by 35
  2. 2023POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Referencecited by 30
  3. 2024UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and UnFavOrable Setscited by 23
  4. 2025E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-trainingcited by 22
  5. 2023Transient Neural Radiance Fields for Lidar View Synthesis and 3D Reconstructioncited by 18
  6. 2024SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wildcited by 18
  7. 2023HyP-NeRF: Learning Improved NeRF Priors using a HyperNetworkcited by 14
  8. 2023UpFusion: Novel View Diffusion from Unposed Sparse View Observationscited by 14
  9. 2023iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse Viewscited by 14
  10. 2025DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusioncited by 14
  11. 2024FAR: Flexible, Accurate and Robust 6DoF Relative Camera Pose Estimationcited by 12
  12. 2024Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesiscited by 9
  13. 2023ID-Pose: Sparse-view Camera Pose Estimation by Inverting Diffusion Modelscited by 8
  14. 2024Extreme Rotation Estimation in the Wildcited by 6
  15. 2025Emergent Extreme-View Geometry in 3D Foundation Modelscited by 6
  16. 2024The More You See in 2D, the More You Perceive in 3Dcited by 5
  17. 2024SRPose: Two-view Relative Pose Estimation with Sparse Keypointscited by 5
  18. 2023MELON: NeRF with Unposed Images in SO(3)cited by 4
  19. 2024Extreme Two-View Geometry From Object Poses with Diffusion Modelscited by 4
  20. 2025Sparse-View 3D Reconstruction: Recent Advances and Open Challengescited by 4
  21. 2023FocalPose++: Focal Length and Object Pose Estimation via Render and Comparecited by 3
  22. 2024ADen: Adaptive Density Representations for Sparse-view Camera Pose Estimationcited by 3
  23. 2024RESfM: Robust Deep Equivariant Structure from Motioncited by 2
  24. 2024NaVIP: An Image-Centric Indoor Navigation Solution for Visually Impaired Peoplecited by 2
  25. 2024Pragmatist: Multiview Conditional Diffusion Models for High-Fidelity 3D Reconstruction from Unposed Sparse Viewscited by 2
  26. 2024WSCLoc: Weakly-Supervised Sparse-View Camera Relocalizationcited by 1
  27. 2025Kaleidoscopic Background Attack: Disrupting Pose Estimation with Multi-Fold Radial Symmetry Texturescited by 1
  28. 2025SERES: Semantic-aware neural reconstruction from sparse viewscited by 1
  29. 2025PoseCrafter: Extreme Pose Estimation with Hybrid Video Synthesiscited by 1
  30. 2026CameraEditor: Camera-Controlled Image Editing via Video-Prior Sequential Modelingcited by 1
  31. 2023LoCUS: Learning Multiscale 3D-consistent Features from Posed Imagescited by 0
  32. 2024Str-L Pose: Integrating Point and Structured Line for Relative Pose Estimation in Dual-Graphcited by 0
  33. 2025FA-BARF: Frequency Adapted Bundle-Adjusting Neural Radiance Fieldscited by 0
  34. 2025GCRayDiffusion: Pose-Free Surface Reconstruction via Geometric Consistent Ray Diffusioncited by 0
  35. 2025T-Graph: Enhancing Sparse-view Camera Pose Estimation by Pairwise Translation Graphcited by 0
  36. 2025Robust Visual Localization via Semantic-Guided Multi-Scale Transformercited by 0
  37. 2026Active Diffusion Matching: Score-based Iterative Alignment of Cross-Modal Retinal Imagescited by 0
  38. 2026Particle Diffusion Matching: Random Walk Correspondence Search for the Alignment of Standard and Ultra-Widefield Fundus Imagescited by 0

50 most cited of 53 All 53 (JSON)