HeatFormer：一种用于多视角人体网格恢复的神经优化器
HeatFormer: A Neural Optimizer for Multiview Human Mesh Recovery
AI总结：
HeatFormer提出一种基于Transformer的神经优化器，通过热图生成与对齐迭代细化SMPL参数，实现多视角人体形状与姿态恢复，具有视角配置不可知性，并在准确性、遮挡鲁棒性和泛化性上表现优异。
摘要：
我们提出了一种新颖的人体形状和姿态恢复方法，能够充分利用多个静态视角。我们针对固定多视角人员监控场景，包括老年人护理和安全监控，在这些场景中，校准相机可以安装在房间或开放空间的角落，但其配置可能因环境而异。我们的关键思想是将此问题表述为神经优化。我们通过HeatFormer实现这一点，这是一种神经优化器，它根据多视角图像迭代地细化SMPL参数，并且从根本上对视角配置具有不可知性。HeatFormer通过一种新颖的Transformer编码器和解码器，将SMPL参数估计实现为热图生成和对齐。我们通过大量实验证明了HeatFormer的有效性，包括其准确性、对遮挡的鲁棒性以及泛化能力。我们相信HeatFormer可以在被动人体行为建模中发挥关键作用。
英文摘要：
We introduce a novel method for human shape and pose recovery that can fully leverage multiple static views. We target fixed-multiview people monitoring, including elderly care and safety monitoring, in which calibrated cameras can be installed at the corners of a room or an open space but whose configuration may vary depending on the environment. Our key idea is to formulate it as neural optimization. We achieve this with HeatFormer, a neural optimizer that iteratively refines the SMPL parameters given multiview images, which is fundamentally agonistic to the configuration of views. HeatFormer realizes this SMPL parameter estimation as heat map generation and alignment with a novel transformer encoder and decoder. We demonstrate the effectiveness of HeatFormer including its accuracy, robustness to occlusion, and generalizability through an extensive set of experiments. We believe HeatFormer can serve a key role in passive human behavior modeling.
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。
