arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.15410cs.CV
收藏

极弱光环境下人体姿态估计

Human Pose Estimation in Extremely Low-Light Conditions

POSTECH(浦项科技大学)

Sohyun Lee, Jaesung Rim, Boseung Jeong, Geonu Kim, Byungju Woo, Haechan Lee, Sunghyun Cho, Suha Kwak

摘要:

我们研究了极低光图像中的人体姿态估计。这项任务具有挑战性,因为难以收集具有准确标签的真实低光图像,并且严重损坏的输入会显着降低预测质量。为了解决第一个问题,我们开发了一个专用的相机系统,并建立了一个新的数据集的真实低光图像与准确的姿势标签。由于我们的相机系统,我们数据集中的每个低光图像都与对齐的光线充足的图像相结合,从而实现了准确的姿势标记,并在训练期间用作特权信息。我们还提出了一个新的模型和一个新的训练策略,充分利用特权信息来学习对光照条件不敏感的表示。我们的方法在真实的极低光图像上表现出出色的性能,广泛的分析验证了我们的模型和数据集都有助于成功。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑