# SDR-GAIN: A High Real-Time Occluded Pedestrian Pose Completion Method for Autonomous Driving

arXiv: https://arxiv.org/abs/2306.03538 · HTML: https://mlsanity.com/paper/2306.03538/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 74 references that are in the map.
- First posted on arXiv 6 Jun 2023.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [RePaint: Inpainting using Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2201.09865/) (2022)
- [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [GAIN: Missing Data Imputation using Generative Adversarial Nets](https://mlsanity.com/paper/1806.02920/) (2018)
- [RMPE: Regional Multi-person Pose Estimation](https://mlsanity.com/paper/1612.00137/) (2016)
- [Scale-recurrent Network for Deep Image Deblurring](https://mlsanity.com/paper/1802.01770/) (2018)
- [Convolutional Pose Machines](https://mlsanity.com/paper/1602.00134/) (2016)
- [HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation](https://mlsanity.com/paper/1908.10357/) (2019)
- [Towards Accurate Multi-person Pose Estimation in the Wild](https://mlsanity.com/paper/1701.01779/) (2017)
- [Human Pose Regression with Residual Log-likelihood Estimation](https://mlsanity.com/paper/2107.11291/) (2021)
- [Joint Training of a Convolutional Network and a Graphical Model for Human Pose Estimation](https://mlsanity.com/paper/1406.2984/) (2014)
- [Human Pose Estimation with Iterative Error Feedback](https://mlsanity.com/paper/1507.06550/) (2015)
- [Motion Planning for Autonomous Driving: The State of the Art and Future Perspectives](https://mlsanity.com/paper/2303.09824/) (2023)
- [DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Model](https://mlsanity.com/paper/1605.03170/) (2016)
- [The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation](https://mlsanity.com/paper/1911.07524/) (2019)
- [Autonomous Vehicles that Interact with Pedestrians: A Survey of Theory and Practice](https://mlsanity.com/paper/1805.11773/) (2018)
- [Rethinking the Heatmap Regression for Bottom-up Human Pose Estimation](https://mlsanity.com/paper/2012.15175/) (2020)
- [SimCC: a Simple Coordinate Classification Perspective for Human Pose Estimation](https://mlsanity.com/paper/2107.03332/) (2021)
- [Human Pose Regression by Combining Indirect Part Detection and Contextual Information](https://mlsanity.com/paper/1710.02322/) (2017)
- [Joint Attention in Autonomous Driving (JAAD)](https://mlsanity.com/paper/1609.04741/) (2016)
- [Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervision](https://mlsanity.com/paper/1911.01138/) (2019)
- [Towards Low Light Enhancement with RAW Images](https://mlsanity.com/paper/2112.14022/) (2021)
- [Is the Pedestrian going to Cross? Answering by 2D Pose Estimation](https://mlsanity.com/paper/1807.10580/) (2018)
- [Spatio-Contextual Deep Network Based Multimodal Pedestrian Detection For Autonomous Driving](https://mlsanity.com/paper/2105.12713/) (2021)
- [Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation](https://mlsanity.com/paper/2206.07510/) (2022)

## Built on by (most cited first, 1 of 1)

- [HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router](https://mlsanity.com/paper/2410.02684/) (2024)

## Abstract (arXiv)

With the advancement of vision-based autonomous driving technology, pedestrian detection have become an important component for improving traffic safety and driving system robustness. Nevertheless, in complex traffic scenarios, conventional pose estimation approaches frequently fail to accurately reconstruct occluded keypoints, primarily due to obstructions caused by vehicles, vegetation, or architectural elements. To address this issue, we propose a novel real-time occluded pedestrian pose completion framework termed Separation and Dimensionality Reduction-based Generative Adversarial Imputation Nets (SDR-GAIN). Unlike previous approaches that train visual models to distinguish occlusion patterns, SDR-GAIN aims to learn human pose directly from the numerical distribution of keypoint coordinates and interpolate missing positions. It employs a self-supervised adversarial learning paradigm to train lightweight generators with residual structures for the imputation of missing pose keypoints. Additionally, it integrates multiple pose standardization techniques to alleviate the difficulty of the learning process. Experiments conducted on the COCO and JAAD datasets demonstrate that SDR-GAIN surpasses conventional machine learning and Transformer-based missing data interpolation algorithms in accurately recovering occluded pedestrian keypoints, while simultaneously achieving microsecond-level real-time inference.