# Neural Descent for Visual 3D Human Pose and Shape

arXiv: https://arxiv.org/abs/2008.06910 · HTML: https://mlsanity.com/paper/2008.06910/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Aug 2020.

## Built on by (most cited first, 30 of 60)

- [PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop](https://mlsanity.com/paper/2103.16507/) (2021)
- [BEHAVE: Dataset and Method for Tracking Human Object Interactions](https://mlsanity.com/paper/2204.06950/) (2022)
- [InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions](https://mlsanity.com/paper/2304.05684/) (2023)
- [Probabilistic Modeling for Human Mesh Recovery](https://mlsanity.com/paper/2108.11944/) (2021)
- [PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images](https://mlsanity.com/paper/2207.06400/) (2022)
- [TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos](https://mlsanity.com/paper/2403.17346/) (2024)
- [Recovering 3D Human Mesh from Monocular Images: A Survey](https://mlsanity.com/paper/2203.01923/) (2022)
- [Capturing and Animation of Body and Clothing from Monocular Video](https://mlsanity.com/paper/2210.01868/) (2022)
- [FLAG: Flow-based 3D Avatar Generation from Sparse Observations](https://mlsanity.com/paper/2203.05789/) (2022)
- [THUNDR: Transformer-based 3D HUmaN Reconstruction with Markers](https://mlsanity.com/paper/2106.09336/) (2021)
- [ReFit: Recurrent Fitting Network for 3D Human Recovery](https://mlsanity.com/paper/2308.11184/) (2023)
- [LiDAR-aid Inertial Poser: Large-scale Human Motion Capture by Sparse Inertial and LiDAR Sensors](https://mlsanity.com/paper/2205.15410/) (2022)
- [Learning Disentangled Avatars with Hybrid 3D Representations](https://mlsanity.com/paper/2309.06441/) (2023)
- [Generative Proxemics: A Prior for 3D Social Interaction from Images](https://mlsanity.com/paper/2306.09337/) (2023)
- [Differentiable Dynamics for Articulated 3d Human Motion Reconstruction](https://mlsanity.com/paper/2205.12256/) (2022)
- [Learned Vertex Descent: A New Direction for 3D Human Model Fitting](https://mlsanity.com/paper/2205.06254/) (2022)
- [Trajectory Optimization for Physics-Based Reconstruction of 3d Human Pose from Monocular Video](https://mlsanity.com/paper/2205.12292/) (2022)
- [LiDARCap: Long-range Marker-less 3D Human Motion Capture with LiDAR Point Clouds](https://mlsanity.com/paper/2203.14698/) (2022)
- [HSPACE: Synthetic Parametric Humans Animated in Complex Environments](https://mlsanity.com/paper/2112.12867/) (2021)
- [Towards Open Domain Text-Driven Synthesis of Multi-Person Motions](https://mlsanity.com/paper/2405.18483/) (2024)
- [Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms](https://mlsanity.com/paper/2209.10529/) (2022)
- [Distribution-Aligned Diffusion for Human Mesh Recovery](https://mlsanity.com/paper/2308.13369/) (2023)
- [ChallenCap: Monocular 3D Capture of Challenging Human Performances using Multi-Modal References](https://mlsanity.com/paper/2103.06747/) (2021)
- [HuManiFlow: Ancestor-Conditioned Normalising Flows on SO(3) Manifolds for Human Pose and Shape Distribution Estimation](https://mlsanity.com/paper/2305.06968/) (2023)
- [LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment](https://mlsanity.com/paper/2402.17171/) (2024)
- [HybridCap: Inertia-aid Monocular Capture of Challenging Human Motions](https://mlsanity.com/paper/2203.09287/) (2022)
- [Fusing Monocular Images and Sparse IMU Signals for Real-time Human Motion Capture](https://mlsanity.com/paper/2309.00310/) (2023)
- [Learning to Fit Morphable Models](https://mlsanity.com/paper/2111.14824/) (2021)
- [BlazePose GHUM Holistic: Real-time 3D Human Landmarks and Pose Estimation](https://mlsanity.com/paper/2206.11678/) (2022)
- [Transformer-Based Learned Optimization](https://mlsanity.com/paper/2212.01055/) (2022)

## Abstract (arXiv)

We present deep neural network methodology to reconstruct the 3d pose and shape of people, given an input RGB image. We rely on a recently introduced, expressivefull body statistical 3d human model, GHUM, trained end-to-end, and learn to reconstruct its pose and shape state in a self-supervised regime. Central to our methodology, is a learning to learn and optimize approach, referred to as HUmanNeural Descent (HUND), which avoids both second-order differentiation when training the model parameters,and expensive state gradient descent in order to accurately minimize a semantic differentiable rendering loss at test time. Instead, we rely on novel recurrent stages to update the pose and shape parameters such that not only losses are minimized effectively, but the process is meta-regularized in order to ensure end-progress. HUND's symmetry between training and testing makes it the first 3d human sensing architecture to natively support different operating regimes including self-supervised ones. In diverse tests, we show that HUND achieves very competitive results in datasets like H3.6M and 3DPW, aswell as good quality 3d reconstructions for complex imagery collected in-the-wild.