mlsanityData to 7 Oct 2026

LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimation

arXiv 1912.00416 ↗First posted 1 Dec 2019cs.CV cs.GR cs.ROcited by 88

Not on the map. Why?

Abstract (arXiv)

Current 6D object pose estimation methods usually require a 3D model for each object. These methods also require additional training in order to incorporate new objects. As a result, they are difficult to scale to a large number of objects and cannot be directly applied to unseen objects. We propose a novel framework for 6D pose estimation of unseen objects. We present a network that reconstructs a latent 3D representation of an object using a small number of reference views at inference time. Our network is able to render the latent 3D representation from arbitrary views. Using this neural renderer, we directly optimize for pose given an input image. By training our network with a large number of 3D shapes for reconstruction and rendering, our network generalizes well to unseen objects. We present a new dataset for unseen object pose estimation--MOPED. We evaluate the performance of our method for unseen object pose estimation on MOPED as well as the ModelNet and LINEMOD datasets. Our method performs competitively to supervised methods that are trained on those objects. Code and data is available at https://keunhong.com/publications/latentfusion/.

Key facts. Cited by 88 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 10; 2022: 21; 2023: 20; 2024: 16; 2025: 10; 2026: 11.

88 papers.

Sort:

By area:

  1. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 411
  2. 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 198
  3. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 155
  4. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  5. 2021FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimationcited by 144
  6. 2023BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objectscited by 144
  7. 2022Gen6D: Generalizable Model-Free 6-DoF Object Pose Estimation from RGB Imagescited by 120
  8. 2023OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Modelscited by 114
  9. 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
  10. 2021BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Modelscited by 87
  11. 2022FS6D: Few-Shot 6D Pose Estimation of Novel Objectscited by 81
  12. 2022NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimationcited by 57
38 more
  1. 2022Few-View Object Reconstruction with Unknown Categories and Camera Posescited by 53
  2. 2021FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modellingcited by 47
  3. 2022PhoCaL: A Multi-Modal Dataset for Category-Level Object Pose Estimation with Photometrically Challenging Objectscited by 45
  4. 2022OVE6D: Object Viewpoint Encoding for Depth-based 6D Object Pose Estimationcited by 43
  5. 2024Deep Learning-Based Object Pose Estimation: A Comprehensive Surveycited by 39
  6. 2025Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrationscited by 33
  7. 2023SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimationcited by 32
  8. 2024GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objectscited by 32
  9. 2023A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospectscited by 30
  10. 2023POPE: 6-DoF Promptable Pose Estimation of Any Object, in Any Scene, with One Referencecited by 30
  11. 2024Line-based 6-DoF Object Pose Estimation and Tracking With an Event Cameracited by 29
  12. 2021ZePHyR: Zero-shot Pose Hypothesis Ratingcited by 26
  13. 2022Uni6D: A Unified CNN Framework without Projection Breakdown for 6D Pose Estimationcited by 22
  14. 2023One-Shot Imitation Learning: A Pose Estimation Perspectivecited by 21
  15. 2023ZeroPose: CAD-Prompted Zero-shot Object 6D Pose Estimation in Cluttered Scenescited by 20
  16. 2021PoseContrast: Class-Agnostic Object Viewpoint Estimation in the Wild with Pose-Aware Contrastive Learningcited by 19
  17. 2022Generative Category-Level Shape and Pose Estimation with Semantic Primitivescited by 19
  18. 2023Learning to Estimate 6DoF Pose from Limited Data: A Few-Shot, Generalizable Approach using RGB Imagescited by 18
  19. 2021Orienting Novel 3D Objects Using Self-Supervised Learning of Rotation Transformscited by 17
  20. 2021PR-GCN: A Deep Graph Convolutional Network with Point Refinement for 6D Pose Estimationcited by 17
  21. 2022Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objectscited by 17
  22. 2025One2Any: One-Reference 6D Pose Estimation for Any Objectcited by 17
  23. 2023Deep Fusion Transformer Network with Weighted Vector-Wise Keypoints Voting for Robust 6D Object Pose Estimationcited by 16
  24. 2022SIMBAR: Single Image-Based Scene Relighting For Effective Data Augmentation For Automated Driving Vision Taskscited by 15
  25. 2022PIZZA: A Powerful Image-only Zero-Shot Zero-CAD Approach to 6 DoF Trackingcited by 15
  26. 2023iFusion: Inverting Diffusion for Pose-Free Reconstruction from Sparse Viewscited by 14
  27. 2024GS-Pose: Generalizable Segmentation-based 6D Object Pose Estimation with 3D Gaussian Splattingcited by 14
  28. 2021DISP6D: Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimationcited by 12
  29. 2022Unseen Object 6D Pose Estimation: A Benchmark and Baselinescited by 12
  30. 2023PoseMatcher: One-shot 6D Object Pose Estimation by Deep Feature Matchingcited by 12
  31. 20233D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimationcited by 11
  32. 2025Scalable Unseen Objects 6-DoF Absolute Pose Estimation with Robotic Integrationcited by 11
  33. 2022COPE: End-to-end trainable Constant Runtime Object Pose Estimationcited by 10
  34. 2023MFOS: Model-Free & One-Shot Object Pose Estimationcited by 10
  35. 2024High-resolution open-vocabulary object 6D pose estimationcited by 10
  36. 20246DOPE-GS: Online 6D Object Pose Estimation using Gaussian Splattingcited by 10
  37. 2021DProST: Dynamic Projective Spatial Transformer Network for 6D Pose Estimationcited by 9
  38. 2022LocPoseNet: Robust Location Prior for Unseen Object Pose Estimationcited by 9

50 most cited of 88 All 88 (JSON)