mlsanityData to 7 Oct 2026

Image to Sphere: Learning Equivariant Features for Efficient Pose Prediction

arXiv 2302.13926 ↗First posted 27 Feb 2023cs.CVcited by 17

Not on the map. Why?

Abstract (arXiv)

Predicting the pose of objects from a single image is an important but difficult computer vision problem. Methods that predict a single point estimate do not predict the pose of objects with symmetries well and cannot represent uncertainty. Alternatively, some works predict a distribution over orientations in SO(3). However, training such models can be computation- and sample-inefficient. Instead, we propose a novel mapping of features from the image domain to the 3D rotation manifold. Our method then leverages SO(3) equivariant layers, which are more sample efficient, and outputs a distribution over rotations that can be sampled at arbitrary resolution. We demonstrate the effectiveness of our method at object orientation prediction, and achieve state-of-the-art performance on the popular PASCAL3D+ dataset. Moreover, we show that our method can model complex object symmetries, without any modifications to the parameters or loss function. Code is available at https://dmklee.github.io/image2sphere.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 27 of its 39 references that are in the map. First posted on arXiv 27 Feb 2023.

Builds on

27 of 39 references.

References · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017Mask R-CNNcited by 7,259
  3. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,186
  4. 2016Group Equivariant Convolutional Networkscited by 1,154
  5. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 768
  6. 2020SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networkscited by 602
  7. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 490
  8. 2018Spherical CNNscited by 452
  9. 2021Vector Neurons: A General Framework for SO(3)-Equivariant Networkscited by 304
  10. 2018Deep Object Pose Estimation for Semantic Robotic Grasping of Household Objectscited by 237
  11. 2019PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimationcited by 204
  12. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
15 more
  1. 2015Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Viewscited by 94
  2. 2021Equivariant Point Network for 3D Point Cloud Analysiscited by 81
  3. 2021Deep Regression on Manifolds: A 3D Rotation Case Studycited by 67
  4. 2018Explorations in Homeomorphic Variational Auto-Encodingcited by 65
  5. 2021Implicit-PDF: Non-Parametric Representation of Probability Distributions on the Rotation Manifoldcited by 65
  6. 2014Viewpoints and Keypointscited by 59
  7. 2022Learning Symmetric Embeddings for Equivariant World Modelscited by 54
  8. 2018Deep Directional Statistics: Pose Estimation with Uncertainty Quantificationcited by 45
  9. 2019Equivariant Multi-View Networkscited by 44
  10. 2020Deep Bingham Networks: Dealing with Uncertainty and Ambiguity in Pose Estimationcited by 43
  11. 2019Spherical Regression: Learning Viewpoints, Surface Normals and 3D Rotations on n-Spherescited by 37
  12. 2020Probabilistic orientation estimation with matrix Fisher distributionscited by 36
  13. 2022CryoAI: Amortized Inference of Poses for Ab Initio Reconstruction of 3D Molecular Volumes from Real Cryo-EM Imagescited by 24
  14. 2018A Mixed Classification-Regression Framework for 3D Pose Estimation from 2D Imagescited by 19
  15. 2018Cross-Domain 3D Equivariant Image Embeddingscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 5; 2025: 3; 2026: 2.

17 papers.

Sort:

By area:

  1. 2024Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3Dcited by 32
  2. 2023PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learningcited by 31
  3. 2023A General Theory of Correct, Incorrect, and Extrinsic Equivariancecited by 18
  4. 2023Confronting Ambiguity in 6D Object Pose Estimation via Score-Based Diffusion on SE(3)cited by 17
  5. 2023Making Vision Transformers Truly Shift-Equivariantcited by 16
  6. 2023SpyroPose: SE(3) Pyramids for Object Pose Distribution Estimationcited by 14
  7. 2025SE(3)-Equivariant Diffusion Policy in Spherical Fourier Spacecited by 7
  8. 2023Equivariant Single View Pose Prediction Via Induced and Restricted Representationscited by 6
  9. 20243D Equivariant Pose Regression via Direct Wigner-D Harmonics Predictioncited by 4
  10. 2024Equivariant Action Sampling for Reinforcement Learning and Planningcited by 4
  11. 20253D Equivariant Visuomotor Policy Learning via Spherical Projectioncited by 4
  12. 2024BOP-Distrib: Revisiting 6D Pose Estimation Benchmarks for Better Evaluation under Visual Ambiguitiescited by 3
5 more
  1. 2024Alignist: CAD-Informed Orientation Distribution Estimation by Fusing Shape and Correspondencescited by 2
  2. 2023Augmenting x-ray single particle imaging reconstruction with self-supervised machine learningcited by 0
  3. 2025Equivariant symmetry-aware head pose estimation for fetal MRIcited by 0
  4. 2026HACMatch Semi-Supervised Rotation Regression with Hardness-Aware Curriculum Pseudo Labelingcited by 0
  5. 2026ARCHER: Amortized cross-specimen pose estimation for cryo-electron microscopycited by 0