# Deep Autoencoder for Combined Human Pose Estimation and body Model Upscaling

arXiv: https://arxiv.org/abs/1807.01511 · HTML: https://mlsanity.com/paper/1807.01511/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jul 2018.

## Built on by (most cited first, 12 of 12)

- [Scene-aware Egocentric 3D Human Pose Estimation](https://mlsanity.com/paper/2212.11684/) (2022)
- [JIFF: Jointly-aligned Implicit Face Function for High Quality Single View Clothed Human Reconstruction](https://mlsanity.com/paper/2204.10549/) (2022)
- [SeSDF: Self-evolved Signed Distance Field for Implicit 3D Clothed Human Reconstruction](https://mlsanity.com/paper/2304.00359/) (2023)
- [Guide3D: Create 3D Avatars from Text and Image Guidance](https://mlsanity.com/paper/2308.09705/) (2023)
- [Progressive Multi-view Human Mesh Recovery with Self-Supervision](https://mlsanity.com/paper/2212.05223/) (2022)
- [FusePose: IMU-Vision Sensor Fusion in Kinematic Space for Parametric Human Pose Estimation](https://mlsanity.com/paper/2208.11960/) (2022)
- [View Consistency Aware Holistic Triangulation for 3D Human Pose Estimation](https://mlsanity.com/paper/2302.11301/) (2023)
- [Human Mesh Recovery from Arbitrary Multi-view Images](https://mlsanity.com/paper/2403.12434/) (2024)
- [Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Images](https://mlsanity.com/paper/2409.18364/) (2024)
- [Multi-view Human Body Mesh Translator](https://mlsanity.com/paper/2210.01886/) (2022)
- [3D Human Scan With A Moving Event Camera](https://mlsanity.com/paper/2404.08504/) (2024)
- [Self-learning Canonical Space for Multi-view 3D Human Pose Estimation](https://mlsanity.com/paper/2403.12440/) (2024)

## Abstract (arXiv)

We present a method for simultaneously estimating 3D human pose and body shape from a sparse set of wide-baseline camera views. We train a symmetric convolutional autoencoder with a dual loss that enforces learning of a latent representation that encodes skeletal joint positions, and at the same time learns a deep representation of volumetric body shape. We harness the latter to up-scale input volumetric data by a factor of 4 ×, whilst recovering a 3D estimate of joint positions with equal or greater accuracy than the state of the art. Inference runs in real-time (25 fps) and has the potential for passive human behaviour monitoring where there is a requirement for high fidelity estimation of human body shape and pose.