# Self-supervised Learning of Motion Capture

arXiv: https://arxiv.org/abs/1712.01337 · HTML: https://mlsanity.com/paper/1712.01337/

## Key facts

- Cited by 97 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Dec 2017.

## Built on by (most cited first, 30 of 97)

- [A Comprehensive Survey on Test-Time Adaptation under Distribution Shifts](https://mlsanity.com/paper/2303.15361/) (2023)
- [PARE: Part Attention Regressor for 3D Human Body Estimation](https://mlsanity.com/paper/2104.08527/) (2021)
- [Mesh Graphormer](https://mlsanity.com/paper/2104.00272/) (2021)
- [PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop](https://mlsanity.com/paper/2103.16507/) (2021)
- [A-NeRF: Articulated Neural Radiance Fields for Learning Human Shape, Appearance, and Pose](https://mlsanity.com/paper/2102.06199/) (2021)
- [AGORA: Avatars in Geography Optimized for Regression Analysis](https://mlsanity.com/paper/2104.14643/) (2021)
- [Capturing and Inferring Dense Full-Body Human-Scene Contact](https://mlsanity.com/paper/2206.09553/) (2022)
- [FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration](https://mlsanity.com/paper/2108.06428/) (2021)
- [SCARF: Self-Supervised Contrastive Learning using Random Feature Corruption](https://mlsanity.com/paper/2106.15147/) (2021)
- [PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images](https://mlsanity.com/paper/2207.06400/) (2022)
- [EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devices](https://mlsanity.com/paper/2112.07642/) (2021)
- [Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimation](https://mlsanity.com/paper/2104.14639/) (2021)
- [SimPoE: Simulated Character Control for 3D Human Pose Estimation](https://mlsanity.com/paper/2104.00683/) (2021)
- [Recovering 3D Human Mesh from Monocular Images: A Survey](https://mlsanity.com/paper/2203.01923/) (2022)
- [Learning Motion Priors for 4D Human Body Capture in 3D Scenes](https://mlsanity.com/paper/2108.10399/) (2021)
- [EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild](https://mlsanity.com/paper/2308.16894/) (2023)
- [Ego-Body Pose Estimation via Ego-Head Pose Estimation](https://mlsanity.com/paper/2212.04636/) (2022)
- [DOVE: Learning Deformable 3D Objects by Watching Videos](https://mlsanity.com/paper/2107.10844/) (2021)
- [S3: Neural Shape, Skeleton, and Skinning Fields for 3D Human Modeling](https://mlsanity.com/paper/2101.06571/) (2021)
- [Multiple Instance Captioning: Learning Representations from Histopathology Textbooks and Articles](https://mlsanity.com/paper/2103.05121/) (2021)
- [HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery](https://mlsanity.com/paper/2304.05690/) (2023)
- [Body Meshes as Points](https://mlsanity.com/paper/2105.02467/) (2021)
- [3D Human Mesh Estimation from Virtual Markers](https://mlsanity.com/paper/2303.11726/) (2023)
- [Animal3D: A Comprehensive Dataset of 3D Animal Pose and Shape](https://mlsanity.com/paper/2308.11737/) (2023)
- [Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild](https://mlsanity.com/paper/2103.10978/) (2021)
- [Bilevel Online Adaptation for Out-of-Domain Human Mesh Reconstruction](https://mlsanity.com/paper/2103.16449/) (2021)
- [Learning to Regress Bodies from Images using Differentiable Semantic Rendering](https://mlsanity.com/paper/2110.03480/) (2021)
- [Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation](https://mlsanity.com/paper/2203.10339/) (2022)
- [Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstruction](https://mlsanity.com/paper/2103.16341/) (2021)
- [A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications](https://mlsanity.com/paper/2206.01038/) (2022)

## Abstract (arXiv)

Current state-of-the-art solutions for motion capture from a single camera are optimization driven: they optimize the parameters of a 3D human model so that its re-projection matches measurements in the video (e.g. person segmentation, optical flow, keypoint detections etc.). Optimization models are susceptible to local minima. This has been the bottleneck that forced using clean green-screen like backgrounds at capture time, manual initialization, or switching to multiple cameras as input resource. In this work, we propose a learning based motion capture model for single camera input. Instead of optimizing mesh and skeleton parameters directly, our model optimizes neural network weights that predict 3D shape and skeleton configurations given a monocular RGB video. Our model is trained using a combination of strong supervision from synthetic data, and self-supervision from differentiable rendering of (a) skeletal keypoints, (b) dense 3D mesh motion, and (c) human-background segmentation, in an end-to-end framework. Empirically we show our model combines the best of both worlds of supervised learning and test-time optimization: supervised learning initializes the model parameters in the right regime, ensuring good pose and surface initialization at test time, without manual effort. Self-supervision by back-propagating through differentiable rendering allows (unsupervised) adaptation of the model to the test data, and offers much tighter fit than a pretrained fixed model. We show that the proposed model improves with experience and converges to low-error solutions where previous optimization methods fail.