mlsanityData to 14 Oct 2026

OmniShape: Zero-Shot Multi-Hypothesis Shape and Pose Estimation in the Real World

arXiv 2508.03669 ↗First posted 5 Aug 2025cs.CV cs.ROcited by 1

Not on the map. Why?

Abstract (arXiv)

We would like to estimate the pose and full shape of an object from a single observation, without assuming known 3D model or category. In this work, we propose OmniShape, the first method of its kind to enable probabilistic pose and shape estimation. OmniShape is based on the key insight that shape completion can be decoupled into two multi-modal distributions: one capturing how measurements project into a normalized object reference frame defined by the dataset and the other modelling a prior over object geometries represented as triplanar neural fields. By training separate conditional diffusion models for these two distributions, we enable sampling multiple hypotheses from the joint pose and shape distribution. OmniShape demonstrates compelling performance on challenging real world datasets. Project website: https://tri-ml.github.io/omnishape

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 46 of its 56 references that are in the map. First posted on arXiv 5 Aug 2025.

Builds on

46 of 56 references.

References · 46

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  4. 2023Segment Anythingcited by 8,234
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  6. 2022Classifier-Free Diffusion Guidancecited by 5,847
  7. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
  8. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  9. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  10. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  11. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  12. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,489
34 more
  1. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  2. 2016Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Networkcited by 1,204
  3. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 938
  4. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 906
  5. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  6. 2023DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creationcited by 843
  7. 2022Point-E: A System for Generating 3D Point Clouds from Complex Promptscited by 699
  8. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  9. 2023One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimizationcited by 560
  10. 2019Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimationcited by 495
  11. 2023Shap-E: Generating Conditional 3D Implicit Functionscited by 385
  12. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 382
  13. 2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 288
  14. 2023One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusioncited by 283
  15. 20223D Neural Field Generation using Triplane Diffusioncited by 274
  16. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
  17. 2018Pix3D: Dataset and Methods for Single-Image 3D Shape Modelingcited by 218
  18. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
  19. 2023BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objectscited by 148
  20. 2023SweetDreamer: Aligning Geometric Priors in 2D Diffusion for Consistent Text-to-3Dcited by 134
  21. 2024Rethinking Inductive Biases for Surface Normal Estimationcited by 124
  22. 2023GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondencecited by 114
  23. 2019PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose Trackingcited by 91
  24. 2019LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimationcited by 89
  25. 20226-DoF Pose Estimation of Household Objects for Robotic Manipulation: An Accessible Dataset and Benchmarkcited by 86
  26. 2022ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimizationcited by 72
  27. 2023Multiview Compressive Coding for 3D Reconstructioncited by 71
  28. 2023GenPose: Generative Category-level Object Pose Estimation via Diffusion Modelscited by 48
  29. 2024SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Viewscited by 35
  30. 2023ZeroShape: Regression-based Zero-shot Shape Reconstructioncited by 30
  31. 2022Pre-train, Self-train, Distill: A simple recipe for Supersizing 3D Reconstructioncited by 26
  32. 2023NeuManifold: Neural Watertight Manifold Reconstruction with Efficient and High-Quality Rendering Supportcited by 25
  33. 2024DiffusionNOCS: Managing Symmetry and Uncertainty in Sim2Real Multi-Modal Category-level Pose Estimationcited by 25
  34. 2022A Real World Dataset for Multi-view 3D Reconstructioncited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observationscited by 7

Similar, not cited

Close in wording, no citation either way

  1. 2022DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion models
  2. 2026Flexible Geometric Guidance for Probabilistic Human Pose Estimation with Diffusion Models
  3. 2025UnPose: Uncertainty-Guided Diffusion Priors for Zero-Shot Pose Estimation
  4. 2024Toward General Object-level Mapping from Sparse Views with 3D Diffusion Priors
  5. 2023Open-Pose 3D Zero-Shot Learning: Benchmark and Challenges
  6. 2026ShapeR: Robust Conditional 3D Shape Generation from Casual Captures
  7. 2025Beyond 'Templates': Category-Agnostic Object Pose, Size, and Shape Estimation from a Single View
  8. 2024Extreme Two-View Geometry From Object Poses with Diffusion Models