mlsanityData to 14 Oct 2026

MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videos

arXiv 2512.10881 ↗First posted 11 Dec 2025cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Motion capture now underpins content creation far beyond digital humans, yet most existing pipelines remain species- or template-specific. We formalize this gap as Category-Agnostic Motion Capture (CAMoCap): given a monocular video and an arbitrary rigged 3D asset as a prompt, the goal is to reconstruct a rotation-based animation such as BVH that directly drives the specific asset. We present MoCapAnything, a reference-guided, factorized framework that first predicts 3D joint trajectories and then recovers asset-specific rotations via constraint-aware inverse kinematics. The system contains three learnable modules and a lightweight IK stage: (1) a Reference Prompt Encoder that extracts per-joint queries from the asset's skeleton, mesh, and rendered images; (2) a Video Feature Extractor that computes dense visual descriptors and reconstructs a coarse 4D deforming mesh to bridge the gap between video and joint space; and (3) a Unified Motion Decoder that fuses these cues to produce temporally coherent trajectories. We also curate Truebones Zoo with 1038 motion clips, each providing a standardized skeleton-mesh-render triad. Experiments on both in-domain benchmarks and in-the-wild videos show that MoCapAnything delivers high-quality skeletal animations and exhibits meaningful cross-species retargeting across heterogeneous rigs, enabling scalable, prompt-driven 3D motion capture for arbitrary assets. Project page: https://animotionlab.github.io/MoCapAnything/

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 44 of its 53 references that are in the map. First posted on arXiv 11 Dec 2025.

Builds on

44 of 53 references.

References · 44

  1. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  2. 2020End-to-End Object Detection with Transformerscited by 7,414
  3. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  4. 2022Objaverse: A Universe of Annotated 3D Objectscited by 1,540
  5. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  6. 2017End-to-end Recovery of Human Shape and Posecited by 885
  7. 2023Objaverse-XL: A Universe of 10M+ 3D Objectscited by 774
  8. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  9. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  10. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 350
  11. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  12. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
32 more
  1. 20163D Menagerie: Modeling the 3D shape and pose of animalscited by 312
  2. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  3. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  4. 2023WHAM: Reconstructing World-grounded Humans with Accurate 3D Motioncited by 206
  5. 2021BANMo: Building Animatable 3D Neural Models from Many Casual Videoscited by 197
  6. 2020Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Videocited by 163
  7. 2021GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Camerascited by 153
  8. 2021Human Pose Regression with Residual Log-likelihood Estimationcited by 131
  9. 2023One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformercited by 130
  10. 2021LASR: Learning Articulated Shape Reconstruction from a Monocular Videocited by 116
  11. 2022MagicPony: Learning Articulated 3D Animals in the Wildcited by 112
  12. 2024TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videoscited by 106
  13. 2024Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shotcited by 101
  14. 2021PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimationcited by 89
  15. 2021SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimationcited by 68
  16. 2022LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discoverycited by 66
  17. 2024Learning the 3D Fauna of the Webcited by 59
  18. 2023Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimationcited by 48
  19. 2023Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimationcited by 47
  20. 2024AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimationcited by 42
  21. 2025AnyTop: Character Animation Diffusion with Any Topologycited by 41
  22. 2022Pose for Everything: Towards Category-Agnostic Pose Estimationcited by 36
  23. 2022CASA: Category-agnostic Skeletal Animal Reconstructioncited by 35
  24. 2023PACE: Human and Camera Motion Estimation from in-the-wild Videoscited by 34
  25. 2024WHAC: World-grounded Humans and Camerascited by 30
  26. 2019Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimationcited by 27
  27. 2022PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervisioncited by 25
  28. 2023A Graph-Based Approach for Category-Agnostic Pose Estimationcited by 17
  29. 2024LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Modelcited by 17
  30. 2022QueryPose: Sparse Multi-Person Pose Regression via Spatial-Aware Part-Level Querycited by 13
  31. 2024Generative Zoocited by 12
  32. 2024CapeX: Category-Agnostic Pose Estimation from Textual Point Explanationcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 10.

10 papers.

  1. 2026MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletonscited by 2
  2. 2026MorphGS: Morphology-Adaptive Articulated 3D Motion Transfer from Videoscited by 1
  3. 2026A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargetingcited by 1
  4. 2026Follow Your Track: Precise Skeleton Animation Controlled by 3D Trajectoriescited by 1
  5. 2026SkelGen4D: Weakly-Supervised Skeleton-Based 4D Generation for Text-Driven Mesh Animationcited by 1
  6. 2026UniMate: One Unified Model to Animate Diverse Skeletonscited by 1
  7. 2026R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flowcited by 0
  8. 2026AnyAct: Towards Human Reenactment of Character Motion From Videocited by 0
  9. 2026SkelMo: Universal Skeletal Motion Generation for 3D Rigged Shapescited by 0
  10. 2026CAST: Real-Time Motion Capture for Any Skeleton Topologycited by 0