# 3D Human Shape Reconstruction from a Polarization Image

arXiv: https://arxiv.org/abs/2007.09268 · HTML: https://mlsanity.com/paper/2007.09268/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Jul 2020.

## Built on by (most cited first, 28 of 28)

- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [Inter-X: Towards Versatile Human-Human Interaction Analysis](https://mlsanity.com/paper/2312.16051/) (2023)
- [Human Motion Generation: A Survey](https://mlsanity.com/paper/2307.10894/) (2023)
- [Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields](https://mlsanity.com/paper/2207.13807/) (2022)
- [PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting](https://mlsanity.com/paper/2210.10542/) (2022)
- [Implicit Neural Representations for Variable Length Human Motion Generation](https://mlsanity.com/paper/2203.13694/) (2022)
- [PhoCaL: A Multi-Modal Dataset for Category-Level Object Pose Estimation with Photometrically Challenging Objects](https://mlsanity.com/paper/2205.08811/) (2022)
- [NeISF: Neural Incident Stokes Field for Geometry and Material Estimation](https://mlsanity.com/paper/2311.13187/) (2023)
- [Human Pose and Shape Estimation from Single Polarization Images](https://mlsanity.com/paper/2108.06834/) (2021)
- [Neural Spectro-polarimetric Fields](https://mlsanity.com/paper/2306.12562/) (2023)
- [Simultaneous Acquisition of High Quality RGB Image and Polarization Information using a Sparse Polarization Sensor](https://mlsanity.com/paper/2209.13106/) (2022)
- [Polarimetric Inverse Rendering for Transparent Shapes Reconstruction](https://mlsanity.com/paper/2208.11836/) (2022)
- [Spectral and Polarization Vision: Spectro-polarimetric Real-world Dataset](https://mlsanity.com/paper/2311.17396/) (2023)
- [Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions](https://mlsanity.com/paper/2508.04681/) (2025)
- [Deep Polarization Cues for Single-shot Shape and Subsurface Scattering Estimation](https://mlsanity.com/paper/2407.08149/) (2024)
- [Spatial-temporal Transformer-guided Diffusion based Data Augmentation for Efficient Skeleton-based Action Recognition](https://mlsanity.com/paper/2302.13434/) (2023)
- [Orientation-Aware Leg Movement Learning for Action-Driven Human Motion Prediction](https://mlsanity.com/paper/2310.14907/) (2023)
- [Learning Joint Representation of Human Motion and Language](https://mlsanity.com/paper/2210.15187/) (2022)
- [Imposing Temporal Consistency on Deep Monocular Body Shape and Pose Estimation](https://mlsanity.com/paper/2202.03074/) (2022)
- [S2P3: Self-Supervised Polarimetric Pose Prediction](https://mlsanity.com/paper/2312.01105/) (2023)
- [Diffusion-based Graph Generative Methods](https://mlsanity.com/paper/2401.15617/) (2024)
- [Frequency-Guided Multi-Level Human Action Anomaly Detection with Normalizing Flows](https://mlsanity.com/paper/2404.17381/) (2024)
- [Polarized Color Image Denoising using Pocoformer](https://mlsanity.com/paper/2207.00215/) (2022)
- [Biologically-Inspired Continual Learning of Human Motion Sequences](https://mlsanity.com/paper/2211.05231/) (2022)
- [Multimodal Generative AI with Autoregressive LLMs for Human Motion Understanding and Generation: A Way Forward](https://mlsanity.com/paper/2506.03191/) (2025)
- [Video Frame Interpolation for Polarization via Swin-Transformer](https://mlsanity.com/paper/2406.11371/) (2024)
- [Generative Data Augmentation for Skeleton Action Recognition](https://mlsanity.com/paper/2604.14933/) (2026)

## Abstract (arXiv)

This paper tackles the problem of estimating 3D body shape of clothed humans from single polarized 2D images, i.e. polarization images. Polarization images are known to be able to capture polarized reflected lights that preserve rich geometric cues of an object, which has motivated its recent applications in reconstructing surface normal of the objects of interest. Inspired by the recent advances in human shape estimation from single color images, in this paper, we attempt at estimating human body shapes by leveraging the geometric cues from single polarization images. A dedicated two-stage deep learning approach, SfP, is proposed: given a polarization image, stage one aims at inferring the fined-detailed body surface normal; stage two gears to reconstruct the 3D body shape of clothing details. Empirical evaluations on a synthetic dataset (SURREAL) as well as a real-world dataset (PHSPD) demonstrate the qualitative and quantitative performance of our approach in estimating human poses and shapes. This indicates polarization camera is a promising alternative to the more conventional color or depth imaging for human shape estimation. Further, normal maps inferred from polarization imaging play a significant role in accurately recovering the body shapes of clothed people.