3D shape reconstruction from a single image is a highly ill-posed problem.
Modern deep learning based systems try to solve this problem by learning an
end-to-end mapping from image to shape via a deep network. In this paper, we
aim to solve this problem via an online optimization framework inspired by
traditional methods. Our framework employs a deep autoencoder to learn a set of
latent codes of 3D object shapes, which are fitted by a probabilistic shape
prior using Gaussian Mixture Model (GMM). At inference, the shape and pose are
jointly optimized guided by both image cues and deep shape prior without
relying on an initialization from any trained deep nets. Surprisingly, our
method achieves comparable performance to state-of-the-art methods even without
training an end-to-end network, which shows a promising step in this direction.

本文提出了一种在线优化的网络结构，通过避免依赖于深层神经网络的初始化，使用了概率形状先验指导深层特征以及图像线索，实现了从单个图像中重建三维形状，且相较于现有最先进方法，得到了可比较的结果。

使用深度形状先验和轮廓的单视图物体形状重建

Single-view Object Shape Reconstruction Using Deep Shape Prior and  Silhouette

Fog computing is emerging as a promising paradigm to perform distributed,
low-latency computation by jointly exploiting the radio and computing resources
of end-user devices and cloud servers. However, the dynamic and distributed
formation of local fog networks is highly challenging due to the unpredictable
arrival and departure of neighboring fog nodes. Therefore, a given fog node
must properly select a set of neighboring nodes and intelligently offload its
computational tasks to this set of neighboring fog nodes and the cloud in order
to achieve low-latency transmission and computation. In this paper, the problem
of fog network formation and task distribution is jointly investigated while
considering a hybrid fog-cloud architecture. The goal is to minimize the
maximum computational latency by enabling a given fog node to form a suitable
fog network and optimize the task distribution, under uncertainty on the
arrival process of neighboring fog nodes. To solve this problem, a novel online
optimization framework is proposed in which the neighboring nodes are selected
by using a threshold-based online algorithm that uses a target competitive
ratio, defined as the ratio between the latency of the online algorithm and the
offline optimal latency. The proposed framework repeatedly updates its target
competitive ratio and optimizes the distribution of the fog node's
computational tasks in order to minimize latency. Simulation results show that
the proposed framework can successfully select a set of neighboring nodes while
reducing latency by up to 19.25% compared to a baseline approach based on the
well-known online secretary framework. The results also show how, using the
proposed framework, the computational tasks can be properly offloaded between
the fog network and a remote cloud server in different network settings.

针对雾计算中存在的不确定性，本文提出了一种在混合雾 - 云架构下，考虑到邻近雾节点到达过程的阈值算法来选择邻居节点，并通过任务分配优化减少延迟的在线优化框架，在不同的网络设置下成功地减少了 19.25% 的延迟，有效地解决了雾节点形成和任务分配问题。