# MoCapAnything V2: End-to-End Motion Capture for Arbitrary Skeletons

arXiv: https://arxiv.org/abs/2604.28130 · HTML: https://mlsanity.com/paper/2604.28130/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 34 references that are in the map.
- First posted on arXiv 30 Apr 2026.

## Builds on (most cited first, 26 of 26)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [VIBE: Video Inference for Human Body Pose and Shape Estimation](https://mlsanity.com/paper/1912.05656/) (2019)
- [3D human pose estimation in video with temporal convolutions and semi-supervised training](https://mlsanity.com/paper/1811.11742/) (2018)
- [Humans in 4D: Reconstructing and Tracking Humans with Transformers](https://mlsanity.com/paper/2305.20091/) (2023)
- [Learning Category-Specific Mesh Reconstruction from Image Collections](https://mlsanity.com/paper/1803.07549/) (2018)
- [3D Menagerie: Modeling the 3D shape and pose of animals](https://mlsanity.com/paper/1611.07700/) (2016)
- [BANMo: Building Animatable 3D Neural Models from Many Casual Videos](https://mlsanity.com/paper/2112.12761/) (2021)
- [LASR: Learning Articulated Shape Reconstruction from a Monocular Video](https://mlsanity.com/paper/2105.02976/) (2021)
- [MagicPony: Learning Articulated 3D Animals in the Wild](https://mlsanity.com/paper/2211.12497/) (2022)
- [LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery](https://mlsanity.com/paper/2207.03434/) (2022)
- [Learning the 3D Fauna of the Web](https://mlsanity.com/paper/2401.02400/) (2024)
- [Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2303.14747/) (2023)
- [AnyTop: Character Animation Diffusion with Any Topology](https://mlsanity.com/paper/2502.17327/) (2025)
- [Pose for Everything: Towards Category-Agnostic Pose Estimation](https://mlsanity.com/paper/2207.10387/) (2022)
- [A Graph-Based Approach for Category-Agnostic Pose Estimation](https://mlsanity.com/paper/2311.17891/) (2023)
- [MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videos](https://mlsanity.com/paper/2512.10881/) (2025)
- [CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation](https://mlsanity.com/paper/2406.00384/) (2024)

## Built on by (most cited first, 2 of 2)

- [AnyAct: Towards Human Reenactment of Character Motion From Video](https://mlsanity.com/paper/2605.15497/) (2026)
- [CAST: Real-Time Motion Capture for Any Skeleton Topology](https://mlsanity.com/paper/2610.14856/) (2026)

## Abstract (arXiv)

Recent methods for arbitrary-skeleton motion capture from monocular video follow a factorized pipeline, where a Video-to-Pose network predicts joint positions and an analytical inverse-kinematics (IK) stage recovers joint rotations. While effective, this design is inherently limited, since joint positions do not fully determine rotations and leave degrees of freedom such as bone-axis twist ambiguous, and the non-differentiable IK stage prevents the system from adapting to noisy predictions or optimizing for the final animation objective. In this work, we present the first fully end-to-end framework in which both Video-to-Pose and Pose-to-Rotation are learnable and jointly optimized. We observe that the ambiguity in pose-to-rotation mapping arises from missing coordinate system information: the same joint positions can correspond to different rotations under different rest poses and local axis conventions. To resolve this, we introduce a reference pose-rotation pair from the target asset, which, together with the rest pose, not only anchors the mapping but also defines the underlying rotation coordinate system. This formulation turns rotation prediction into a well-constrained conditional problem and enables effective learning. In addition, our model predicts joint positions directly from video without relying on mesh intermediates, improving both robustness and efficiency. Both stages share a skeleton-aware Global-Local Graph-guided Multi-Head Attention (GL-GMHA) module for joint-level local reasoning and global coordination. Experiments on Truebones Zoo and Objaverse show that our method reduces rotation error from ~17 degrees to ~10 degrees, and to 6.54 degrees on unseen skeletons, while achieving ~20x faster inference than mesh-based pipelines. Project page: https://animotionlab.github.io/MoCapAnythingV2/