TY - JOUR AU - Gärtner, Erik AU - Pirinen, Aleksis AU - Sminchisescu, Cristian PY - 2020/04/03 Y2 - 2024/03/28 TI - Deep Reinforcement Learning for Active Human Pose Estimation JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 34 IS - 07 SE - AAAI Technical Track: Vision DO - 10.1609/aaai.v34i07.6714 UR - https://ojs.aaai.org/index.php/AAAI/article/view/6714 SP - 10835-10844 AB - <p>Most 3d human pose estimation methods assume that input – be it images of a scene collected from one or several viewpoints, or from a video – is given. Consequently, they focus on estimates leveraging prior knowledge and measurement by fusing information spatially and/or temporally, whenever available. In this paper we address the problem of an active observer with freedom to move and explore the scene spatially – in ‘time-freeze’ mode – and/or temporally, by selecting informative viewpoints that improve its estimation accuracy. Towards this end, we introduce <em>Pose-DRL</em>, a fully trainable deep reinforcement learning-based active pose estimation architecture which learns to select appropriate views, in space and time, to feed an underlying monocular pose estimator. We evaluate our model using single- and multi-target estimators with strong result in both settings. Our system further learns automatic stopping conditions in time and transition functions to the next temporal processing step in videos. In extensive experiments with the Panoptic multi-view setup, and for complex scenes containing multiple people, we show that our model learns to select viewpoints that yield significantly more accurate pose estimates compared to strong multi-view baselines.</p> ER -