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.

翻译：我们研究了极端弱光图像中的人体姿态估计问题。该任务面临两大挑战：一是难以收集带有精确标注的真实弱光图像，二是严重退化的输入会显著降低预测质量。针对第一个问题，我们开发了专用相机系统并构建了包含精确姿态标注的真实弱光图像新数据集。得益于相机系统，数据集中每张弱光图像均配有对齐的良好光照图像，这不仅实现了精确的姿态标注，还在训练过程中作为特权信息使用。我们同时提出了新模型与新训练策略，能够充分利用特权信息学习对光照条件不敏感的表示。该方法在真实极端弱光图像上展现出卓越性能，大量分析验证表明，我们的模型与数据集共同促成了该成功。