mlsanityData to 7 Oct 2026

Human Pose Estimation in Extremely Low-Light Conditions

arXiv 2303.15410 ↗First posted 27 Mar 2023cs.CVcited by 27

Not on the map. Why?

Abstract (arXiv)

We study human pose estimation in extremely low-light images. This task is challenging due to the difficulty of collecting real low-light images with accurate labels, and severely corrupted inputs that degrade prediction quality significantly. To address the first issue, we develop a dedicated camera system and build a new dataset of real low-light images with accurate pose labels. Thanks to our camera system, each low-light image in our dataset is coupled with an aligned well-lit image, which enables accurate pose labeling and is used as privileged information during training. We also propose a new model and a new training strategy that fully exploit the privileged information to learn representation insensitive to lighting conditions. Our method demonstrates outstanding performance on real extremely low light images, and extensive analyses validate that both of our model and dataset contribute to the success.

Key facts. Cited by 27 papers in the map (data through 7 Oct 2026). Builds on 46 of its 81 references that are in the map. First posted on arXiv 27 Mar 2023.

Builds on

46 of 81 references.

References · 46

  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. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2015Domain-Adversarial Training of Neural Networkscited by 3,023
  7. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  8. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  9. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  10. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  11. 2018Deep Anomaly Detection with Outlier Exposurecited by 939
  12. 2018Deep Retinex Decomposition for Low-Light Enhancementcited by 720
34 more
  1. 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
  2. 2018DensePose: Dense Human Pose Estimation In The Wildcited by 573
  3. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
  4. 2019EnlightenGAN: Deep Light Enhancement without Paired Supervisioncited by 466
  5. 2018Learning to See in the Darkcited by 459
  6. 2020Improving robustness against common corruptions by covariate shift adaptationcited by 427
  7. 2017Semantic Foggy Scene Understanding with Synthetic Datacited by 401
  8. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  9. 2013DeepPose: Human Pose Estimation via Deep Neural Networkscited by 305
  10. 2015LLNet: A Deep Autoencoder Approach to Natural Low-light Image Enhancementcited by 224
  11. 2015Unifying distillation and privileged informationcited by 218
  12. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  13. 2019Domain-Specific Batch Normalization for Unsupervised Domain Adaptationcited by 197
  14. 2021Low-Light Image Enhancement with Normalizing Flowcited by 184
  15. 2018Getting to Know Low-light Images with The Exclusively Dark Datasetcited by 157
  16. 2020A Physics-based Noise Formation Model for Extreme Low-light Raw Denoisingcited by 138
  17. 2019Cross-Domain Adaptation for Animal Pose Estimationcited by 108
  18. 2018Pose2Seg: Detection Free Human Instance Segmentationcited by 107
  19. 2018Model Adaptation with Synthetic and Real Data for Semantic Dense Foggy Scene Understandingcited by 98
  20. 2019Single Image Deraining: A Comprehensive Benchmark Analysiscited by 84
  21. 2018Fast Human Pose Estimationcited by 68
  22. 2021Physics-based Noise Modeling for Extreme Low-light Photographycited by 67
  23. 2020Informative Dropout for Robust Representation Learning: A Shape-bias Perspectivecited by 57
  24. 2022Realistic Blur Synthesis for Learning Image Deblurringcited by 51
  25. 2020ARID: A New Dataset for Recognizing Action in the Darkcited by 42
  26. 2019Curriculum Model Adaptation with Synthetic and Real Data for Semantic Foggy Scene Understandingcited by 40
  27. 2022FIFO: Learning Fog-invariant Features for Foggy Scene Segmentationcited by 31
  28. 2021HLA-Face: Joint High-Low Adaptation for Low Light Face Detectioncited by 28
  29. 2020URIE: Universal Image Enhancement for Visual Recognition in the Wildcited by 27
  30. 2020Recurrent Exposure Generation for Low-Light Face Detectioncited by 27
  31. 2018Deep Learning under Privileged Information Using Heteroscedastic Dropoutcited by 26
  32. 2021NOD: Taking a Closer Look at Detection under Extreme Low-Light Conditions with Night Object Detection Datasetcited by 12
  33. 2021Matching in the Dark: A Dataset for Matching Image Pairs of Low-light Scenescited by 7
  34. 2013Privileged Information for Data Clusteringcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 12; 2025: 6; 2026: 8.

27 papers.

Sort:

By area:

  1. 2024Towards Robust Event-guided Low-Light Image Enhancement: A Large-Scale Real-World Event-Image Dataset and Novel Approachcited by 48
  2. 2024Multi-Object Tracking in the Darkcited by 14
  3. 2024EvLight++: Low-Light Video Enhancement with an Event Camera: A Large-Scale Real-World Dataset, Novel Method, and Morecited by 13
  4. 2024FREST: Feature RESToration for Semantic Segmentation under Multiple Adverse Conditionscited by 7
  5. 2024Domain-Adaptive 2D Human Pose Estimation via Dual Teachers in Extremely Low-Light Conditionscited by 7
  6. 2024Unsupervised Image Prior via Prompt Learning and CLIP Semantic Guidance for Low-Light Image Enhancementcited by 6
  7. 2024Improving Low-Light Image Recognition Performance Based on Image-adaptive Learnable Modulecited by 2
  8. 2024Acoustic-based 3D Human Pose Estimation Robust to Human Positioncited by 2
  9. 2024Leveraging Content and Context Cues for Low-Light Image Enhancementcited by 2
  10. 2026Event-Illumination Collaborative Low-light Image Enhancement with a High-resolution Real-world Datasetcited by 2
  11. 2023Towards Effective Collaborative Learning in Long-Tailed Recognitioncited by 1
  12. 2024Troublemaker Learning for Low-Light Image Enhancementcited by 1
15 more
  1. 2024Depth-based Privileged Information for Boosting 3D Human Pose Estimation on RGBcited by 1
  2. 2025Robust Low-Light Human Pose Estimation through Illumination-Texture Modulationcited by 1
  3. 2025BGM2Pose: Active 3D Human Pose Estimation with Non-Stationary Soundscited by 1
  4. 2025VST-Pose: A Velocity-Integrated Spatiotem-poral Attention Network for Human WiFi Pose Estimationcited by 1
  5. 2026EgoXtreme: A Dataset for Robust Object Pose Estimation in Egocentric Views under Extreme Conditionscited by 1
  6. 2026UDAPose: Unsupervised Domain Adaptation for Low-Light Human Pose Estimationcited by 1
  7. 2024Cross-Domain Knowledge Distillation for Low-Resolution Human Pose Estimationcited by 0
  8. 2025Recognition-Oriented Low-Light Image Enhancement based on Global and Pixelwise Optimizationcited by 0
  9. 2025ELVIS: Enhance Low-Light for Video Instance Segmentation in the Darkcited by 0
  10. 2025DarkQA: Benchmarking Vision-Language Models on Visual-Primitive Question Answering in Low-Light Indoor Scenescited by 0
  11. 2026LiDAR-Anchored Collaborative Distillation for Robust 2D Representationscited by 0
  12. 2026MERIT: Multi-domain Efficient RAW Image Translationcited by 0
  13. 2026Robust Promptable Video Object Segmentationcited by 0
  14. 2026LUMINA-26: Low-Light Understanding for Modeling and Interpreting Night-time Actionscited by 0
  15. 2026Sound-based Multi-Person 3D Pose Estimationcited by 0