# Domain-Adaptive 2D Human Pose Estimation via Dual Teachers in Extremely Low-Light Conditions arXiv: https://arxiv.org/abs/2407.15451 ยท HTML: https://mlsanity.com/paper/2407.15451/ ## Key facts - Cited by 7 papers in the map (data through 14 Oct 2026). - Builds on 46 of its 60 references that are in the map. - First posted on arXiv 22 Jul 2024. ## Builds on (most cited first, 30 of 46) - [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014) - [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017) - [Domain-Adversarial Training of Neural Networks](https://mlsanity.com/paper/1505.07818/) (2015) - [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017) - [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019) - [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018) - [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018) - [ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation](https://mlsanity.com/paper/1811.12833/) (2018) - [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022) - [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018) - [Cascaded Pyramid Network for Multi-Person Pose Estimation](https://mlsanity.com/paper/1711.07319/) (2017) - [HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation](https://mlsanity.com/paper/1908.10357/) (2019) - [Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement](https://mlsanity.com/paper/2303.06705/) (2023) - [CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark](https://mlsanity.com/paper/1812.00324/) (2018) - [Associative Embedding: End-to-End Learning for Joint Detection and Grouping](https://mlsanity.com/paper/1611.05424/) (2016) - [Low-Light Image Enhancement with Normalizing Flow](https://mlsanity.com/paper/2109.05923/) (2021) - [A Physics-based Noise Formation Model for Extreme Low-light Raw Denoising](https://mlsanity.com/paper/2003.12751/) (2020) - [Learning non-maximum suppression](https://mlsanity.com/paper/1705.02950/) (2017) - [Bottom-Up Human Pose Estimation Via Disentangled Keypoint Regression](https://mlsanity.com/paper/2104.02300/) (2021) - [AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion Sensing](https://mlsanity.com/paper/2207.13784/) (2022) - [Cross-Domain Adaptation for Animal Pose Estimation](https://mlsanity.com/paper/1908.05806/) (2019) - [Pose2Seg: Detection Free Human Instance Segmentation](https://mlsanity.com/paper/1803.10683/) (2018) - [DeepLPF: Deep Local Parametric Filters for Image Enhancement](https://mlsanity.com/paper/2003.13985/) (2020) - [Towards Multi-pose Guided Virtual Try-on Network](https://mlsanity.com/paper/1902.11026/) (2019) - [Unsupervised Night Image Enhancement: When Layer Decomposition Meets Light-Effects Suppression](https://mlsanity.com/paper/2207.10564/) (2022) - [Physics-based Noise Modeling for Extreme Low-light Photography](https://mlsanity.com/paper/2108.02158/) (2021) - [Learning from Synthetic Animals](https://mlsanity.com/paper/1912.08265/) (2019) - [Photo Wake-Up: 3D Character Animation from a Single Photo](https://mlsanity.com/paper/1812.02246/) (2018) - [DirectPose: Direct End-to-End Multi-Person Pose Estimation](https://mlsanity.com/paper/1911.07451/) (2019) - [From Synthetic to Real: Unsupervised Domain Adaptation for Animal Pose Estimation](https://mlsanity.com/paper/2103.14843/) (2021) ## Built on by (most cited first, 7 of 7) - [EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection](https://mlsanity.com/paper/2410.23904/) (2024) - [Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation](https://mlsanity.com/paper/2504.03193/) (2025) - [ER-LoRA: Effective-Rank Guided Adaptation for Weather-Generalized Depth Estimation](https://mlsanity.com/paper/2509.00665/) (2025) - [From Sharp to Blur: Unsupervised Domain Adaptation for 2D Human Pose Estimation Under Extreme Motion Blur Using Event Cameras](https://mlsanity.com/paper/2507.22438/) (2025) - [UDAPose: Unsupervised Domain Adaptation for Low-Light Human Pose Estimation](https://mlsanity.com/paper/2604.10485/) (2026) - [Actor as Its Own Critic: Unifying Region Understanding and Localization via CycleGRPO](https://mlsanity.com/paper/2607.11581/) (2026) - [IELDG: Suppressing Domain-Specific Noise with Inverse Evolution Layers for Domain Generalized Semantic Segmentation](https://mlsanity.com/paper/2508.19604/) (2025) ## Abstract (arXiv) Existing 2D human pose estimation research predominantly concentrates on well-lit scenarios, with limited exploration of poor lighting conditions, which are a prevalent aspect of daily life. Recent studies on low-light pose estimation require the use of paired well-lit and low-light images with ground truths for training, which are impractical due to the inherent challenges associated with annotation on low-light images. To this end, we introduce a novel approach that eliminates the need for low-light ground truths. Our primary novelty lies in leveraging two complementary-teacher networks to generate more reliable pseudo labels, enabling our model achieves competitive performance on extremely low-light images without the need for training with low-light ground truths. Our framework consists of two stages. In the first stage, our model is trained on well-lit data with low-light augmentations. In the second stage, we propose a dual-teacher framework to utilize the unlabeled low-light data, where a center-based main teacher produces the pseudo labels for relatively visible cases, while a keypoints-based complementary teacher focuses on producing the pseudo labels for the missed persons of the main teacher. With the pseudo labels from both teachers, we propose a person-specific low-light augmentation to challenge a student model in training to outperform the teachers. Experimental results on real low-light dataset (ExLPose-OCN) show, our method achieves 6.8% (2.4 AP) improvement over the state-of-the-art (SOTA) method, despite no low-light ground-truth data is used in our approach, in contrast to the SOTA method. Our code will be available at:https://github.com/ayh015-dev/DA-LLPose.