We propose a novel algorithm for the fitting of 3D human shape to images. Combining the accuracy and refinement capabilities of iterative gradient-based optimization techniques with the robustness of deep neural networks, we propose a gradient descent algorithm that leverages a neural network to predict the parameter update rule for each iteration. This per-parameter and state-aware update guides the optimizer towards a good solution in very few steps, converging in typically few steps. During training our approach only requires MoCap data of human poses, parametrized via SMPL. From this data the network learns a subspace of valid poses and shapes in which optimization is performed much more efficiently. The approach does not require any hard to acquire image-to-3D correspondences. At test time we only optimize the 2D joint re-projection error without the need for any further priors or regularization terms. We show empirically that this algorithm is fast (avg. 120ms convergence), robust to initialization and dataset, and achieves state-of-the-art results on public evaluation datasets including the challenging 3DPW in-the-wild benchmark (improvement over SMPLify 45%) and also approaches using image-to-3D correspondences
Learned Vertex Descent: A New Direction for 3D Human Model Fitting
University of Tübingen（图宾根大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Institut de Robòtica i Informàtica Industrial, CSIC-UPC（西班牙高等科学研究理事会-加泰罗尼亚理工大学工业机器人与信息学研究所）
DULDA: Dual-domain Unsupervised Learned Descent Algorithm for PET image reconstruction
Zhejiang University（浙江大学）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；University of Florida（佛罗里达大学）；Massachusetts General Brigham（麻省总医院布莱根医疗系统）
即插即用（Plug-and-Play，PSTO）框架使得将先进的图像去噪先验集成到优化算法中成为可能，从而有效地解决了通常被公式化为最大后验概率（Maximum A Posteriori，MAP）估计问题的各种图像恢复任务。即插即用交替方向乘法器（ADMM）和去噪正则化（RED）算法是这类方法的两个例子，在图像恢复方面取得了突破。然而，虽然前一种方法只适用于近似算法，但最近已经表明，当去噪器缺乏雅可比对称性时，不存在解释RED算法的正则化，这恰好是大多数实际去噪器的情况。据我们所知，没有一种方法可以训练直接表示正则化器梯度的网络，这可以直接用于即插即用的基于梯度的算法。我们表明，它是可能的训练网络直接建模的MAP正则化梯度，同时共同训练相应的MAP去噪。我们使用这个网络在基于梯度的优化方法，并获得更好的结果相比，其他通用的即插即用的方法。我们还证明了正则化器可以用作展开梯度下降的预训练网络。最后，我们表明，由此产生的去噪器允许一个更好的收敛的即插即用ADMM。
