mlsanityData to 7 Oct 2026

StackFLOW: Monocular Human-Object Reconstruction by Stacked Normalizing Flow with Offset

arXiv 2407.20545 ↗First posted 30 Jul 2024cs.CV cs.GRcited by 5

Not on the map. Why?

Abstract (arXiv)

Modeling and capturing the 3D spatial arrangement of the human and the object is the key to perceiving 3D human-object interaction from monocular images. In this work, we propose to use the Human-Object Offset between anchors which are densely sampled from the surface of human mesh and object mesh to represent human-object spatial relation. Compared with previous works which use contact map or implicit distance filed to encode 3D human-object spatial relations, our method is a simple and efficient way to encode the highly detailed spatial correlation between the human and object. Based on this representation, we propose Stacked Normalizing Flow (StackFLOW) to infer the posterior distribution of human-object spatial relations from the image. During the optimization stage, we finetune the human body pose and object 6D pose by maximizing the likelihood of samples based on this posterior distribution and minimizing the 2D-3D corresponding reprojection loss. Extensive experimental results show that our method achieves impressive results on two challenging benchmarks, BEHAVE and InterCap datasets.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 34 of its 44 references that are in the map. First posted on arXiv 30 Jul 2024.

Builds on

34 of 44 references.

References · 34

  1. 2015Variational Inference with Normalizing Flowscited by 2,161
  2. 2016Density estimation using Real NVPcited by 2,029
  3. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  4. 2017End-to-end Recovery of Human Shape and Posecited by 883
  5. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  6. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  7. 2019Resolving 3D Human Pose Ambiguities with 3D Scene Constraintscited by 294
  8. 2022BEHAVE: Dataset and Method for Tracking Human Object Interactionscited by 246
  9. 2017SSD-6D: Making RGB-based 3D detection and 6D pose estimation great againcited by 243
  10. 2020Deep Global Registrationcited by 228
  11. 2017Detecting and Recognizing Human-Object Interactionscited by 199
  12. 2020Grasping Field: Learning Implicit Representations for Human Graspscited by 178
22 more
  1. 2022Capturing and Inferring Dense Full-Body Human-Scene Contactcited by 176
  2. 2020Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wildcited by 152
  3. 2021Probabilistic Modeling for Human Mesh Recoverycited by 152
  4. 2020VSGNet: Spatial Attention Network for Detecting Human Object Interactions Using Graph Convolutionscited by 115
  5. 2022CHORE: Contact, Human and Object REconstruction from a single RGB imagecited by 95
  6. 2022InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interactioncited by 90
  7. 2019Pose-aware Multi-level Feature Network for Human Object Interaction Detectioncited by 88
  8. 2023EPro-PnP: Generalized End-to-End Probabilistic Perspective-n-Points for Monocular Object Pose Estimationcited by 79
  9. 2021MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Imagescited by 78
  10. 2019Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsensecited by 71
  11. 2022NeuralDome: A Neural Modeling Pipeline on Multi-View Human-Object Interactionscited by 67
  12. 2023Visibility Aware Human-Object Interaction Tracking from Single RGB Cameracited by 58
  13. 2020Holistic 3D Human and Scene Mesh Estimation from Single View Imagescited by 54
  14. 2022FLAG: Flow-based 3D Avatar Generation from Sparse Observationscited by 54
  15. 2021Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wildcited by 40
  16. 2021Neural Free-Viewpoint Performance Rendering under Complex Human-object Interactionscited by 37
  17. 2021ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Posescited by 35
  18. 20206D Camera Relocalization in Ambiguous Scenes via Continuous Multimodal Inferencecited by 23
  19. 2022HybridCap: Inertia-aid Monocular Capture of Challenging Human Motionscited by 19
  20. 2023IKOL: Inverse kinematics optimization layer for 3D human pose and shape estimation via Gauss-Newton differentiationcited by 9
  21. 2022HandFlow: Quantifying View-Dependent 3D Ambiguity in Two-Hand Reconstruction with Normalizing Flowcited by 5
  22. 2021Human Object Interaction Detection using Two-Direction Spatial Enhancement and Exclusive Object Priorcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 2; 2026: 2.

5 papers.

  1. 2024InterTrack: Tracking Human Object Interaction without Object Templatescited by 22
  2. 2025Reconstructing 4D Spatial Intelligence: A Surveycited by 13
  3. 2025End-to-End HOI Reconstruction Transformer with Graph-based Encodingcited by 8
  4. 2026MaMi-HOI: Harmonizing Global Kinematics and Local Geometry for Human-Object Interaction Generationcited by 0
  5. 2026Reconstructing Humans and Objects in Interaction using Large Reconstruction Modelscited by 0