mlsanityData to 7 Oct 2026

POISE: Pose Guided Human Silhouette Extraction under Occlusions

arXiv 2311.05077 ↗First posted 9 Nov 2023cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

Human silhouette extraction is a fundamental task in computer vision with applications in various downstream tasks. However, occlusions pose a significant challenge, leading to incomplete and distorted silhouettes. To address this challenge, we introduce POISE: Pose Guided Human Silhouette Extraction under Occlusions, a novel self-supervised fusion framework that enhances accuracy and robustness in human silhouette prediction. By combining initial silhouette estimates from a segmentation model with human joint predictions from a 2D pose estimation model, POISE leverages the complementary strengths of both approaches, effectively integrating precise body shape information and spatial information to tackle occlusions. Furthermore, the self-supervised nature of POISE eliminates the need for costly annotations, making it scalable and practical. Extensive experimental results demonstrate its superiority in improving silhouette extraction under occlusions, with promising results in downstream tasks such as gait recognition. The code for our method is available https://github.com/take2rohit/poise.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 34 of its 57 references that are in the map. First posted on arXiv 9 Nov 2023.

Builds on

34 of 57 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  6. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  7. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  8. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
  9. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,048
  10. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  11. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  12. 2017Random Erasing Data Augmentationcited by 1,235
22 more
  1. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
  2. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  3. 2017A simple yet effective baseline for 3d human pose estimationcited by 401
  4. 2015Learning Deconvolution Network for Semantic Segmentationcited by 365
  5. 2017Learning from Synthetic Humanscited by 358
  6. 2017Unite the People: Closing the Loop Between 3D and 2D Human Representationscited by 205
  7. 2019Self-Correction for Human Parsingcited by 179
  8. 2020BlendMask: Top-Down Meets Bottom-Up for Instance Segmentationcited by 144
  9. 2017Look into Person: Self-supervised Structure-sensitive Learning and A New Benchmark for Human Parsingcited by 109
  10. 2022OpenGait: Revisiting Gait Recognition Toward Better Practicalitycited by 85
  11. 2018Look into Person: Joint Body Parsing & Pose Estimation Network and A New Benchmarkcited by 79
  12. 2018Fast Human Pose Estimationcited by 68
  13. 2022Expanding Accurate Person Recognition to New Altitudes and Ranges: The BRIAR Datasetcited by 61
  14. 20203D Human Pose Estimation using Spatio-Temporal Networks with Explicit Occlusion Trainingcited by 54
  15. 2021Regressive Domain Adaptation for Unsupervised Keypoint Detectioncited by 34
  16. 2021Human De-occlusion: Invisible Perception and Recovery for Humanscited by 31
  17. 2020Peeking into occluded joints: A novel framework for crowd pose estimationcited by 25
  18. 2022Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimationcited by 25
  19. 2022A Unified Framework for Domain Adaptive Pose Estimationcited by 20
  20. 2020Correlating Edge, Pose with Parsingcited by 18
  21. 2023Prior-guided Source-free Domain Adaptation for Human Pose Estimationcited by 13
  22. 2022Explicit Occlusion Reasoning for Multi-person 3D Human Pose Estimationcited by 10

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 2; 2025: 1.

5 papers.

  1. 2025CHROME: Clothed Human Reconstruction with Occlusion-Resilience and Multiview-Consistency from a Single Imagecited by 6
  2. 2023STRIDE: Single-video based Temporally Continuous Occlusion-Robust 3D Pose Estimationcited by 2
  3. 2024DMAT: A Dynamic Mask-Aware Transformer for Human De-occlusioncited by 1
  4. 2024POSTURE: Pose Guided Unsupervised Domain Adaptation for Human Body Part Segmentationcited by 1
  5. 2023Repurposing SAM for User-Defined Semantics Aware Segmentationcited by 0