mlsanityData to 14 Oct 2026

ID-Pose: Sparse-view Camera Pose Estimation by Inverting Diffusion Models

arXiv 2306.17140 ↗First posted 29 Jun 2023cs.CVcited by 8

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

Given sparse views of a 3D object, estimating their camera poses is a long-standing and intractable problem. Toward this goal, we consider harnessing the pre-trained diffusion model of novel views conditioned on viewpoints (Zero-1-to-3). We present ID-Pose which inverses the denoising diffusion process to estimate the relative pose given two input images. ID-Pose adds a noise to one image, and predicts the noise conditioned on the other image and a hypothesis of the relative pose. The prediction error is used as the minimization objective to find the optimal pose with the gradient descent method. We extend ID-Pose to handle more than two images and estimate each pose with multiple image pairs from triangular relations. ID-Pose requires no training and generalizes to open-world images. We conduct extensive experiments using casually captured photos and rendered images with random viewpoints. The results demonstrate that ID-Pose significantly outperforms state-of-the-art methods.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 30 of its 39 references that are in the map. First posted on arXiv 29 Jun 2023.

Builds on

30 of 39 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar

Other references · 29

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  5. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
  6. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  7. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  8. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  9. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,351
  10. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  11. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  12. 2023LightGlue: Local Feature Matching at Light Speedcited by 590
17 more
  1. 2018From Coarse to Fine: Robust Hierarchical Localization at Large Scalecited by 559
  2. 2020INeRF: Inverting Neural Radiance Fields for Pose Estimationcited by 382
  3. 2021GAN Inversion: A Surveycited by 367
  4. 2021ABO: Dataset and Benchmarks for Real-World 3D Object Understandingcited by 366
  5. 2016Generative Visual Manipulation on the Natural Image Manifoldcited by 348
  6. 2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 326
  7. 2021Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representationscited by 227
  8. 2022SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstructioncited by 216
  9. 2022Highly Accurate Dichotomous Image Segmentationcited by 110
  10. 2022RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wildcited by 102
  11. 2023RelPose++: Recovering 6D Poses from Sparse-view Observationscited by 87
  12. 2022ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformerscited by 70
  13. 2018MVDepthNet: Real-time Multiview Depth Estimation Neural Networkcited by 59
  14. 2022SparsePose: Sparse-View Camera Pose Regression and Refinementcited by 53
  15. 2022Few-View Object Reconstruction with Unknown Categories and Camera Posescited by 53
  16. 2023NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotationscited by 53
  17. 2017Relative Camera Pose Estimation Using Convolutional Neural Networkscited by 47

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 6; 2025: 1; 2026: 1.

8 papers.

  1. 2024UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and UnFavOrable Setscited by 23
  2. 2024SHINOBI: Shape and Illumination using Neural Object Decomposition via BRDF Optimization In-the-wildcited by 18
  3. 2024Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesiscited by 9
  4. 2025Sparse-View 3D Reconstruction: Recent Advances and Open Challengescited by 4
  5. 2024Pragmatist: Multiview Conditional Diffusion Models for High-Fidelity 3D Reconstruction from Unposed Sparse Viewscited by 2
  6. 20243D Congealing: 3D-Aware Image Alignment in the Wildcited by 1
  7. 2024Generalizable Single-view Object Pose Estimation by Two-side Generating and Matchingcited by 1
  8. 2026Landscape-Awareness for Geometric View Diffusion Modelcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Cameras as Rays: Pose Estimation via Ray Diffusion
  2. 2025MonoSE(3)-Diffusion: A Monocular SE(3) Diffusion Framework for Robust Camera-to-Robot Pose Estimation
  3. 2023iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse Views
  4. 2024Object Pose Estimation via the Aggregation of Diffusion Features
  5. 2022DiffPose: Toward More Reliable 3D Pose Estimation
  6. 2024D3PRefiner: A Diffusion-based Denoise Method for 3D Human Pose Refinement
  7. 2022DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion models
  8. 2024Extreme Two-View Geometry From Object Poses with Diffusion Models