Polarization Human Shape and Pose Dataset
Not on the map. Why?
Abstract (arXiv)
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 detailed surface normal of the objects of interest. Meanwhile, inspired by the recent breakthroughs in human shape estimation from a single color image, we attempt to investigate the new question of whether the geometric cues from polarization camera could be leveraged in estimating detailed human body shapes. This has led to the curation of Polarization Human Shape and Pose Dataset (PHSPD), our home-grown polarization image dataset of various human shapes and poses.
Key facts. Cited by 10 papers in the map (data through 13 Oct 2026). First posted on arXiv 30 Apr 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 2; 2022: 2; 2023: 1; 2024: 2; 2025: 2; 2026: 1.
10 papers.
- 2021BABEL: Bodies, Action and Behavior with English Labelscited by 263
- 2022PoseGPT: Quantization-based 3D Human Motion Generation and Forecastingcited by 78
- 2022Action-conditioned On-demand Motion Generationcited by 18
- 2023Spatial-temporal Transformer-guided Diffusion based Data Augmentation for Efficient Skeleton-based Action Recognitioncited by 4
- 2025Animating the Uncaptured: Humanoid Mesh Animation with Video Diffusion Modelscited by 3
- 2024Diffusion-based Graph Generative Methodscited by 2
- 2021OR-Net: Pointwise Relational Inference for Data Completion under Partial Observationcited by 0
- 2024Video Frame Interpolation for Polarization via Swin-Transformercited by 0
- 2025Understanding the Representation of Older Adults in Motion Capture Locomotion Datasetscited by 0
- 2026Generative Data Augmentation for Skeleton Action Recognitioncited by 0
- 2026Generative Data Augmentation for Skeleton Action Recognition16 Apr 2026
- 2025Understanding the Representation of Older Adults in Motion Capture Locomotion Datasets12 Nov 2025
- 2025Animating the Uncaptured: Humanoid Mesh Animation with Video Diffusion Models20 Mar 2025
- 2024Video Frame Interpolation for Polarization via Swin-Transformer17 Jun 2024
- 2024Diffusion-based Graph Generative Methods28 Jan 2024
- 2023Spatial-temporal Transformer-guided Diffusion based Data Augmentation for Efficient Skeleton-based Action Recognition26 Feb 2023
- 2022PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting19 Oct 2022
- 2022Action-conditioned On-demand Motion Generation17 Jul 2022
- 2021BABEL: Bodies, Action and Behavior with English Labels17 Jun 2021
- 2021OR-Net: Pointwise Relational Inference for Data Completion under Partial Observation2 May 2021