mlsanityData to 14 Oct 2026

Foundational feature fusion for conditional flow matching in 6D pose estimation

arXiv 2608.29183 ↗First posted 29 Aug 2026cs.CVcited by 0

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

Abstract (arXiv)

Conditional flow matching has enabled a step forward in object 6D pose estimation, achieving state-of-the-art performance by progressively denoising and registering object representations to observed scenes. Existing methods require training task-specific encoders supervised on object-scene overlap and rely on trivial feature fusion strategies to resolve pose ambiguities. We present FunFlow6D, a novel flow matching-based formulation that leverages features from geometric and appearance foundation models for pose estimation, eliminating the need for task-specific encoder training. We also introduce a cross attention-based fusion mechanism that dynamically combines geometric and appearance features to provide richer conditioning for the flow matching module. Experiments on four datasets from the BOP benchmark show that FunFlow6D outperforms the previous state of the art while reducing supervision requirements and memory overhead. Extensive ablations validate the contribution of each proposed component. Project website: https://tev-fbk.github.io/FunFlow6D/.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 36 of its 46 references that are in the map. First posted on arXiv 29 Aug 2026.

Builds on

36 of 46 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026Generative 6D Pose Estimation via Conditional Flow Matching23 Feb
  2. 2025Register Any Point: Scaling 3D Point Cloud Registration by Flow Matching1 Dec

Other references · 34

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  4. 2022Flow Matching for Generative Modelingcited by 5,702
  5. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  6. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  7. 2025DINOv3cited by 1,414
  8. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  9. 2023Point Transformer V3: Simpler, Faster, Strongercited by 589
  10. 2020CosyPose: Consistent multi-view multi-object 6D pose estimationcited by 287
  11. 2025Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Freecited by 283
  12. 2018BOP: Benchmark for 6D Object Pose Estimationcited by 254
22 more
  1. 2019Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimationcited by 218
  2. 2018PPFNet: Global Context Aware Local Features for Robust 3D Point Matchingcited by 181
  3. 2021GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimatorcited by 148
  4. 2022ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimationcited by 116
  5. 2023FoundPose: Unseen Object Pose Estimation with Foundation Featurescited by 109
  6. 2021SurfEmb: Dense and Continuous Correspondence Distributions for Object Pose Estimation with Learnt Surface Embeddingscited by 95
  7. 2015Recovering 6D Object Pose and Predicting Next-Best-View in the Crowdcited by 79
  8. 2024BOP Challenge 2023 on Detection, Segmentation and Pose Estimation of Seen and Unseen Rigid Objectscited by 60
  9. 2023FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation modelscited by 57
  10. 2022Coupled Iterative Refinement for 6D Multi-Object Pose Estimationcited by 48
  11. 2021Learning general and distinctive 3D local deep descriptors for point cloud registrationcited by 42
  12. 2022Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimationcited by 32
  13. 2026Utonia: Toward One Encoder for All Point Cloudscited by 21
  14. 2025Rectified Point Flow: Generic Point Cloud Pose Estimationcited by 14
  15. 2020A Hybrid Approach for 6DoF Pose Estimationcited by 13
  16. 2025GARF: Learning Generalizable 3D Reassembly for Real-World Fracturescited by 13
  17. 2025Accurate and efficient zero-shot 6D pose estimation with frozen foundation modelscited by 13
  18. 2026TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignmentcited by 13
  19. 2025Distilling 3D distinctive local descriptors for 6D pose estimationcited by 4
  20. 2025SE(3)-PoseFlow: Estimating 6D Pose Distributions for Uncertainty-Aware Robotic Manipulationcited by 4
  21. 2025HccePose(BF): Predicting Front & Back Surfaces to Construct Ultra-Dense 2D-3D Correspondences for Pose Estimationcited by 3
  22. 2025CHIP: A multi-sensor dataset for 6D pose estimation of chairs in industrial settingscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Flow6D: Discrete-to-Continuous Flow Matching for Efficient and Accurate Category-Level 6D Pose Estimation
  2. 2026RFM-Pose:Reinforcement-Guided Flow Matching for Fast Category-Level 6D Pose Estimation
  3. 2026OMNI-PoseX: A Fast Vision Model for 6D Object Pose Estimation in Embodied Tasks ↗
  4. 2025VLM6D: VLM based 6Dof Pose Estimation based on RGB-D Images
  5. 2026Posterior Augmented Flow Matching
  6. 2026UniPose9D: Universal Category-Agnostic Object Pose Estimation
  7. 2022Knowledge Distillation for 6D Pose Estimation by Aligning Distributions of Local Predictions
  8. 2025AxisPose: Model-Free Matching-Free Single-Shot 6D Object Pose Estimation via Axis Generation