mlsanityData to 14 Oct 2026

SCFlow2: Plug-and-Play Object Pose Refiner with Shape-Constraint Scene Flow

arXiv 2504.09160 ↗First posted 12 Apr 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

We introduce SCFlow2, a plug-and-play refinement framework for 6D object pose estimation. Most recent 6D object pose methods rely on refinement to get accurate results. However, most existing refinement methods either suffer from noises in establishing correspondences, or rely on retraining for novel objects. SCFlow2 is based on the SCFlow model designed for refinement with shape constraint, but formulates the additional depth as a regularization in the iteration via 3D scene flow for RGBD frames. The key design of SCFlow2 is an introduction of geometry constraints into the training of recurrent matching network, by combining the rigid-motion embeddings in 3D scene flow and 3D shape prior of the target. We train SCFlow2 on a combination of dataset Objaverse, GSO and ShapeNet, and evaluate on BOP datasets with novel objects. After using our method as a post-processing, most state-of-the-art methods produce significantly better results, without any retraining or fine-tuning. The source code is available at https://scflow2.github.io.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 44 of its 53 references that are in the map. First posted on arXiv 12 Apr 2025.

Builds on

44 of 53 references.

References · 44

  1. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  2. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,401
  3. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,897
  4. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  5. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  6. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,304
  7. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  8. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  9. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 612
  10. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 429
  11. 2018PVNet: Pixel-wise Voting Network for 6DoF Pose Estimationcited by 385
  12. 2019DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusioncited by 355
32 more
  1. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  2. 2018DeepIM: Deep Iterative Matching for 6D Pose Estimationcited by 283
  3. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
  4. 2017BB8: A Scalable, Accurate, Robust to Partial Occlusion Method for Predicting the 3D Poses of Challenging Objects without Using Depthcited by 225
  5. 2017T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-less Objectscited by 210
  6. 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 201
  7. 2019DPOD: 6D Pose Object Detector and Refinercited by 189
  8. 2022OnePose: One-Shot Object Pose Estimation without CAD Modelscited by 157
  9. 2020EPOS: Estimating 6D Pose of Objects with Symmetriescited by 148
  10. 2020RAFT-3D: Scene Flow using Rigid-Motion Embeddingscited by 122
  11. 2023SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimationcited by 117
  12. 2022ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimationcited by 116
  13. 2023The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimationcited by 116
  14. 2023GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondencecited by 114
  15. 2019HomebrewedDB: RGB-D Dataset for 6D Pose Estimation of 3D Objectscited by 110
  16. 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
  17. 2020HybridPose: 6D Object Pose Estimation under Hybrid Representationscited by 107
  18. 2021SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddingscited by 95
  19. 2019LatentFusion: End-to-End Differentiable Reconstruction and Rendering for Unseen Object Pose Estimationcited by 89
  20. 2019Single-Stage 6D Object Pose Estimationcited by 88
  21. 2022FS6D: Few-Shot 6D Pose Estimation of Novel Objectscited by 81
  22. 2022OSOP: A Multi-Stage One Shot Object Pose Estimation Frameworkcited by 81
  23. 2015Recovering 6D Object Pose and Predicting Next-Best-View in the Crowdcited by 79
  24. 2019End-to-End Learnable Geometric Vision by Backpropagating PnP Optimizationcited by 65
  25. 2021Wide-Depth-Range 6D Object Pose Estimation in Spacecited by 45
  26. 2023NOPE: Novel Object Pose Estimation from a Single Imagecited by 38
  27. 2023Optical flow estimation from event-based cameras and spiking neural networkscited by 33
  28. 2024GenFlow: Generalizable Recurrent Flow for 6D Pose Refinement of Novel Objectscited by 33
  29. 2022Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimationcited by 32
  30. 2023HiPose: Hierarchical Binary Surface Encoding and Correspondence Pruning for RGB-D 6DoF Object Pose Estimationcited by 17
  31. 2023Pseudo Flow Consistency for Self-Supervised 6D Object Pose Estimationcited by 9
  32. 2023Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Exploring 6D Object Pose Estimation with Deformationcited by 0