# Learning from Abstract Images: on the Importance of Occlusion in a Minimalist Encoding of Human Poses

arXiv: https://arxiv.org/abs/2307.09893 · HTML: https://mlsanity.com/paper/2307.09893/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 41 references that are in the map.
- First posted on arXiv 19 Jul 2023.

## Builds on (most cited first, 30 of 30)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [3D human pose estimation in video with temporal convolutions and semi-supervised training](https://mlsanity.com/paper/1811.11742/) (2018)
- [A simple yet effective baseline for 3d human pose estimation](https://mlsanity.com/paper/1705.03098/) (2017)
- [Learning from Synthetic Humans](https://mlsanity.com/paper/1701.01370/) (2017)
- [Learning to Estimate 3D Hand Pose from Single RGB Images](https://mlsanity.com/paper/1705.01389/) (2017)
- [Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose](https://mlsanity.com/paper/1611.07828/) (2016)
- [Semantic Graph Convolutional Networks for 3D Human Pose Regression](https://mlsanity.com/paper/1904.03345/) (2019)
- [VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera](https://mlsanity.com/paper/1705.01583/) (2017)
- [Compositional Human Pose Regression](https://mlsanity.com/paper/1704.00159/) (2017)
- [3D Human Pose Estimation = 2D Pose Estimation + Matching](https://mlsanity.com/paper/1612.06524/) (2016)
- [Ordinal Depth Supervision for 3D Human Pose Estimation](https://mlsanity.com/paper/1805.04095/) (2018)
- [Unsupervised 3D Pose Estimation with Geometric Self-Supervision](https://mlsanity.com/paper/1904.04812/) (2019)
- [SRNet: Improving Generalization in 3D Human Pose Estimation with a Split-and-Recombine Approach](https://mlsanity.com/paper/2007.09389/) (2020)
- [Generating Multiple Hypotheses for 3D Human Pose Estimation with Mixture Density Network](https://mlsanity.com/paper/1904.05547/) (2019)
- [PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation](https://mlsanity.com/paper/2105.02465/) (2021)
- [3D Human Pose Estimation in the Wild by Adversarial Learning](https://mlsanity.com/paper/1803.09722/) (2018)
- [RepNet: Weakly Supervised Training of an Adversarial Reprojection Network for 3D Human Pose Estimation](https://mlsanity.com/paper/1902.09868/) (2019)
- [Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking](https://mlsanity.com/paper/1904.01324/) (2019)
- [3D Human Pose Estimation from a Single Image via Distance Matrix Regression](https://mlsanity.com/paper/1611.09010/) (2016)
- [HEMlets Pose: Learning Part-Centric Heatmap Triplets for Accurate 3D Human Pose Estimation](https://mlsanity.com/paper/1910.12032/) (2019)
- [In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representations](https://mlsanity.com/paper/1904.03289/) (2019)
- [Self-Supervised 3D Human Pose Estimation via Part Guided Novel Image Synthesis](https://mlsanity.com/paper/2004.04400/) (2020)
- [Structured Prediction of 3D Human Pose with Deep Neural Networks](https://mlsanity.com/paper/1605.05180/) (2016)
- [Deep Kinematic Pose Regression](https://mlsanity.com/paper/1609.05317/) (2016)
- [Maximum-Margin Structured Learning with Deep Networks for 3D Human Pose Estimation](https://mlsanity.com/paper/1508.06708/) (2015)
- [Predicting Camera Viewpoint Improves Cross-dataset Generalization for 3D Human Pose Estimation](https://mlsanity.com/paper/2004.03143/) (2020)
- [ElePose: Unsupervised 3D Human Pose Estimation by Predicting Camera Elevation and Learning Normalizing Flows on 2D Poses](https://mlsanity.com/paper/2112.07088/) (2021)
- [DRPose3D: Depth Ranking in 3D Human Pose Estimation](https://mlsanity.com/paper/1805.08973/) (2018)
- [Learning camera viewpoint using CNN to improve 3D body pose estimation](https://mlsanity.com/paper/1609.05522/) (2016)

## Abstract (arXiv)

Existing 2D-to-3D pose lifting networks suffer from poor performance in cross-dataset benchmarks. Although the use of 2D keypoints joined by "stick-figure" limbs has shown promise as an intermediate step, stick-figures do not account for occlusion information that is often inherent in an image. In this paper, we propose a novel representation using opaque 3D limbs that preserves occlusion information while implicitly encoding joint locations. Crucially, when training on data with accurate three-dimensional keypoints and without part-maps, this representation allows training on abstract synthetic images, with occlusion, from as many synthetic viewpoints as desired. The result is a pose defined by limb angles rather than joint positions unicodex2013 because poses are, in the real world, independent of cameras unicodex2013 allowing us to predict poses that are completely independent of camera viewpoint. The result provides not only an improvement in same-dataset benchmarks, but a "quantum leap" in cross-dataset benchmarks.