mlsanityData to 7 Oct 2026

SpyroPose: SE(3) Pyramids for Object Pose Distribution Estimation

arXiv 2303.05308 ↗First posted 9 Mar 2023cs.CV cs.ROcited by 14

Not on the map. Why?

Abstract (arXiv)

Object pose estimation is a core computer vision problem and often an essential component in robotics. Pose estimation is usually approached by seeking the single best estimate of an object's pose, but this approach is ill-suited for tasks involving visual ambiguity. In such cases it is desirable to estimate the uncertainty as a pose distribution to allow downstream tasks to make informed decisions. Pose distributions can have arbitrary complexity which motivates estimating unparameterized distributions, however, until now they have only been used for orientation estimation on SO(3) due to the difficulty in training on and normalizing over SE(3). We propose a novel method for pose distribution estimation on SE(3). We use a hierarchical grid, a pyramid, which enables efficient importance sampling during training and sparse evaluation of the pyramid at inference, allowing real time 6D pose distribution estimation. Our method outperforms state-of-the-art methods on SO(3), and to the best of our knowledge, we provide the first quantitative results on pose distribution estimation on SE(3). Code will be available at spyropose.github.io

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 24 of its 32 references that are in the map. First posted on arXiv 9 Mar 2023.

Builds on

24 of 32 references.

References · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  5. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  6. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  7. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  8. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  9. 2017T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objectscited by 210
  10. 2020BOP Challenge 2020 on 6D Object Localizationcited by 192
  11. 2019Implicit 3D Orientation Learning for 6D Object Detection from RGB Imagescited by 170
  12. 2020EPOS: Estimating 6D Pose of Objects with Symmetriescited by 147
12 more
  1. 2019HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objectscited by 110
  2. 2021SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddingscited by 95
  3. 2019PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Trackingcited by 91
  4. 2018Explaining the Ambiguity of Object Detection and 6D Pose From Visual Datacited by 68
  5. 2021Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifoldcited by 65
  6. 2018Deep Directional Statistics: Pose Estimation with Uncertainty Quantificationcited by 45
  7. 2020Deep Bingham Networks: Dealing with Uncertainty and Ambiguity in Pose Estimationcited by 43
  8. 2020Learning Orientation Distributions for Object Pose Estimationcited by 18
  9. 2020Fast Uncertainty Quantification for Deep Object Pose Estimationcited by 18
  10. 2023Image to Sphere: Learning Equivariant Features for Efficient Pose Predictioncited by 17
  11. 2022Ki-Pode: Keypoint-based Implicit Pose Distribution Estimation of Rigid Objectscited by 7
  12. 2022Multi-view object pose estimation from correspondence distributions and epipolar geometrycited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 6; 2026: 3.

14 papers.

Sort:

By area:

  1. 2024MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Imagescited by 28
  2. 2025GCE-Pose: Global Context Enhancement for Category-level Object Pose Estimationcited by 16
  3. 2024BOP-Distrib: Revisiting 6D Pose Estimation Benchmarks for Better Evaluation under Visual Ambiguitiescited by 3
  4. 2025Active 6D Pose Estimation for Textureless Objects using Multi-View RGB Framescited by 3
  5. 2025Corr2Distrib: Making Ambiguous Correspondences an Ally to Predict Reliable 6D Pose Distributionscited by 3
  6. 2024Alignist: CAD-Informed Orientation Distribution Estimation by Fusing Shape and Correspondencescited by 2
  7. 2024End-to-End Probabilistic Geometry-Guided Regression for 6DoF Object Pose Estimationcited by 2
  8. 2025Object Pose Distribution Estimation for Determining Revolution and Reflection Uncertainty in Point Cloudscited by 1
  9. 2026Towards Symmetry-sensitive Pose Estimation: A Rotation Representation for Symmetric Object Classescited by 1
  10. 2024SABER-6D: Shape Representation Based Implicit Object Pose Estimationcited by 0
  11. 2025Consensus-Driven Uncertainty for Robotic Grasping based on RGB Perceptioncited by 0
  12. 2025Aleatoric Uncertainty from AI-based 6D Object Pose Predictors for Object-relative State Estimationcited by 0
2 more
  1. 2026Landscape-Awareness for Geometric View Diffusion Modelcited by 0
  2. 2026Towards a Modular Bin-picking Framework for Handling Object Pose Uncertaintiescited by 0