This paper considers to jointly tackle the highly correlated tasks of estimating 3D human body poses and predicting future 3D motions from RGB image sequences. Based on Lie algebra pose representation, a novel self-projection mechanism is proposed that naturally preserves human motion kinematics. This is further facilitated by a sequence-to-sequence multi-task architecture based on an encoder-decoder topology, which enables us to tap into the common ground shared by both tasks. Finally, a global refinement module is proposed to boost the performance of our framework. The effectiveness of our approach, called PoseMoNet, is demonstrated by ablation tests and empirical evaluations on Human3.6M and HumanEva-I benchmark, where competitive performance is obtained comparing to the state-of-the-arts.
翻译:本文件考虑共同处理估算3D人体构成的高度关联性任务,并预测未来RGB图像序列中的3D运动。根据Lie代数代表,建议建立一个新颖的自我预测机制,自然保存人类运动运动运动动力学。基于编码器脱coder-decoder 地形学的顺序到序列的多任务结构,使我们能够利用两个任务的共同点。最后,提议了一个全球改进模块,以提高我们框架的绩效。我们的方法,即PoseMoNet,通过人类3.6M 和 HumanEva-I 基准的模拟测试和经验评估,展示了我们方法的有效性。