# Learning Variational Motion Prior for Video-based Motion Capture

arXiv: https://arxiv.org/abs/2210.15134 · HTML: https://mlsanity.com/paper/2210.15134/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 62 references that are in the map.
- First posted on arXiv 27 Oct 2022.

## Builds on (most cited first, 30 of 31)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016)
- [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://mlsanity.com/paper/1909.12828/) (2019)
- [VIBE: Video Inference for Human Body Pose and Shape Estimation](https://mlsanity.com/paper/1912.05656/) (2019)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [Action2Motion: Conditioned Generation of 3D Human Motions](https://mlsanity.com/paper/2007.15240/) (2020)
- [PARE: Part Attention Regressor for 3D Human Body Estimation](https://mlsanity.com/paper/2104.08527/) (2021)
- [HuMoR: 3D Human Motion Model for Robust Pose Estimation](https://mlsanity.com/paper/2105.04668/) (2021)
- [Learning 3D Human Dynamics from Video](https://mlsanity.com/paper/1812.01601/) (2018)
- [HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2011.14672/) (2020)
- [Video Based Reconstruction of 3D People Models](https://mlsanity.com/paper/1803.04758/) (2018)
- [Unite the People: Closing the Loop Between 3D and 2D Human Representations](https://mlsanity.com/paper/1701.02468/) (2017)
- [STAR: Sparse Trained Articulated Human Body Regressor](https://mlsanity.com/paper/2008.08535/) (2020)
- [Character Controllers Using Motion VAEs](https://mlsanity.com/paper/2103.14274/) (2021)
- [DeepCap: Monocular Human Performance Capture Using Weak Supervision](https://mlsanity.com/paper/2003.08325/) (2020)
- [DoubleFusion: Real-time Capture of Human Performances with Inner Body Shapes from a Single Depth Sensor](https://mlsanity.com/paper/1804.06023/) (2018)
- [Contact and Human Dynamics from Monocular Video](https://mlsanity.com/paper/2007.11678/) (2020)
- [LiveCap: Real-time Human Performance Capture from Monocular Video](https://mlsanity.com/paper/1810.02648/) (2018)
- [VolumeDeform: Real-time Volumetric Non-rigid Reconstruction](https://mlsanity.com/paper/1603.08161/) (2016)
- [MonoPerfCap: Human Performance Capture from Monocular Video](https://mlsanity.com/paper/1708.02136/) (2017)
- [Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation](https://mlsanity.com/paper/2109.02303/) (2021)
- [Estimating 3D Motion and Forces of Person-Object Interactions from Monocular Video](https://mlsanity.com/paper/1904.02683/) (2019)
- [SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos](https://mlsanity.com/paper/2104.11452/) (2021)

## Built on by (most cited first, 17 of 17)

- [Executing your Commands via Motion Diffusion in Latent Space](https://mlsanity.com/paper/2212.04048/) (2022)
- [OmniControl: Control Any Joint at Any Time for Human Motion Generation](https://mlsanity.com/paper/2310.08580/) (2023)
- [Guided Motion Diffusion for Controllable Human Motion Synthesis](https://mlsanity.com/paper/2305.12577/) (2023)
- [InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions](https://mlsanity.com/paper/2304.05684/) (2023)
- [Optimizing Diffusion Noise Can Serve As Universal Motion Priors](https://mlsanity.com/paper/2312.11994/) (2023)
- [TLControl: Trajectory and Language Control for Human Motion Synthesis](https://mlsanity.com/paper/2311.17135/) (2023)
- [EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation](https://mlsanity.com/paper/2312.02256/) (2023)
- [ParCo: Part-Coordinating Text-to-Motion Synthesis](https://mlsanity.com/paper/2403.18512/) (2024)
- [HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors](https://mlsanity.com/paper/2406.12459/) (2024)
- [OMG: Towards Open-vocabulary Motion Generation via Mixture of Controllers](https://mlsanity.com/paper/2312.08985/) (2023)
- [Disentangled Clothed Avatar Generation from Text Descriptions](https://mlsanity.com/paper/2312.05295/) (2023)
- [ReinDiffuse: Crafting Physically Plausible Motions with Reinforced Diffusion Model](https://mlsanity.com/paper/2410.07296/) (2024)
- [HMD-Poser: On-Device Real-time Human Motion Tracking from Scalable Sparse Observations](https://mlsanity.com/paper/2403.03561/) (2024)
- [Text-driven Human Motion Generation with Motion Masked Diffusion Model](https://mlsanity.com/paper/2409.19686/) (2024)
- [BiPO: Bidirectional Partial Occlusion Network for Text-to-Motion Synthesis](https://mlsanity.com/paper/2412.00112/) (2024)
- [A Self-Supervised Approach on Motion Calibration for Enhancing Physical Plausibility in Text-to-Motion](https://mlsanity.com/paper/2602.18199/) (2026)
- [Retargeting Motions to Diverse Skeletons via Learnable Flattening](https://mlsanity.com/paper/2609.38578/) (2026)

## Abstract (arXiv)

Motion capture from a monocular video is fundamental and crucial for us humans to naturally experience and interact with each other in Virtual Reality (VR) and Augmented Reality (AR). However, existing methods still struggle with challenging cases involving self-occlusion and complex poses due to the lack of effective motion prior modeling. In this paper, we present a novel variational motion prior (VMP) learning approach for video-based motion capture to resolve the above issue. Instead of directly building the correspondence between the video and motion domain, We propose to learn a generic latent space for capturing the prior distribution of all natural motions, which serve as the basis for subsequent video-based motion capture tasks. To improve the generalization capacity of prior space, we propose a transformer-based variational autoencoder pretrained over marker-based 3D mocap data, with a novel style-mapping block to boost the generation quality. Afterward, a separate video encoder is attached to the pretrained motion generator for end-to-end fine-tuning over task-specific video datasets. Compared to existing motion prior models, our VMP model serves as a motion rectifier that can effectively reduce temporal jittering and failure modes in frame-wise pose estimation, leading to temporally stable and visually realistic motion capture results. Furthermore, our VMP-based framework models motion at sequence level and can directly generate motion clips in the forward pass, achieving real-time motion capture during inference. Extensive experiments over both public datasets and in-the-wild videos have demonstrated the efficacy and generalization capability of our framework.