mlsanityData to 7 Oct 2026

MorphGS: Morphology-Adaptive Articulated 3D Motion Transfer from Videos

arXiv 2601.02716 ↗First posted 6 Jan 2026cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

Transferring articulated motion from monocular videos to rigged 3D characters is challenging due to pose ambiguity in 2D observations and morphological differences between source and target. Existing approaches often follow a reconstruct-then-retarget paradigm, tying transfer quality to intermediate 3D reconstruction and limiting applicability to categories with parametric templates. We propose MorphGS, a framework that formulates motion retargeting as a target-driven analysis-by-synthesis problem, directly optimizing target morphology and pose through image-space supervision. A rig-coupled morphology parameterization factorizes character identity from time-varying joint rotations, while dense 2D-3D correspondences and synthesized views provide complementary structural and multi-view guidance. Experiments on synthetic benchmarks and real-world videos show consistent improvements over baselines. Project page: https://xodus777.github.io/MorphGS/

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 61 of its 79 references that are in the map. First posted on arXiv 6 Jan 2026.

Builds on

61 of 79 references.

References · 61

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  4. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  5. 2023Zero-1-to-3: Zero-shot One Image to 3D Objectcited by 1,483
  6. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,144
  7. 2016A Point Set Generation Network for 3D Object Reconstruction from a Single Imagecited by 972
  8. 2017End-to-end Recovery of Human Shape and Posecited by 883
  9. 2025SAM 3: Segment Anything with Conceptscited by 835
  10. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 781
  11. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 344
  12. 2023SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenescited by 339
38 more
  1. 20163D Menagerie: Modeling the 3D shape and pose of animalscited by 310
  2. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  3. 2021BANMo: Building Animatable 3D Neural Models from Many Casual Videoscited by 195
  4. 2023GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussianscited by 190
  5. 2022Physical Inertial Poser (PIP): Physics-aware Real-time Human Motion Tracking from Sparse Inertial Sensorscited by 144
  6. 20214DComplete: Non-Rigid Motion Estimation Beyond the Observable Surfacecited by 123
  7. 2020Skeleton-Aware Networks for Deep Motion Retargetingcited by 118
  8. 2022MagicPony: Learning Articulated 3D Animals in the Wildcited by 111
  9. 2018Neural Kinematic Networks for Unsupervised Motion Retargettingcited by 85
  10. 2023Telling Left from Right: Identifying Geometry-Aware Semantic Correspondencecited by 85
  11. 2018Learning Monocular 3D Human Pose Estimation from Multi-view Imagescited by 70
  12. 2022LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discoverycited by 65
  13. 2024SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglementcited by 65
  14. 2020Unsupervised Shape and Pose Disentanglement for 3D Meshescited by 61
  15. 2021DOVE: Learning Deformable 3D Objects by Watching Videoscited by 61
  16. 2024SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfercited by 61
  17. 2024Learning the 3D Fauna of the Webcited by 58
  18. 2024DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representationcited by 58
  19. 2024Fr'echet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videoscited by 54
  20. 2022BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Informationcited by 51
  21. 2025SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generationcited by 44
  22. 2025One Model to Rig Them All: Diverse Skeleton Rigging with UniRigcited by 44
  23. 2025MagicArticulate: Make Your 3D Models Articulation-Readycited by 43
  24. 2025Puppeteer: Rig and Animate Your 3D Modelscited by 41
  25. 2020Neural Pose Transfer by Spatially Adaptive Instance Normalizationcited by 37
  26. 2023Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusioncited by 37
  27. 2020TransMoMo: Invariance-Driven Unsupervised Video Motion Retargetingcited by 36
  28. 2021Contact-Aware Retargeting of Skinned Motioncited by 31
  29. 2015Learning Analysis-by-Synthesis for 6D Pose Estimation in RGB-D Imagescited by 29
  30. 2022Skeleton-free Pose Transfer for Stylized 3D Characterscited by 29
  31. 2024Animal Avatars: Reconstructing Animatable 3D Animals from Casual Videoscited by 26
  32. 2020Monocular Differentiable Rendering for Self-Supervised 3D Object Detectioncited by 23
  33. 2024AniMer: Animal Pose and Shape Estimation Using Family Aware Transformercited by 20
  34. 2024MagicPose4D: Crafting Articulated Models with Appearance and Motion Controlcited by 18
  35. 2023SAOR: Single-View Articulated Object Reconstructioncited by 15
  36. 2023Template-free Articulated Neural Point Clouds for Reposable View Synthesiscited by 15
  37. 2025RigGS: Rigging of 3D Gaussians for Modeling Articulated Objects in Videoscited by 14
  38. 2023Zero-shot Pose Transfer for Unrigged Stylized 3D Characterscited by 12

50 most cited of 61 All 61 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction from Video Priorscited by 0