Deep learning-based multi-view stereo (MVS) methods enable dense point cloud reconstruction in texture-rich areas. However, existing methods incur significant computational costs to capture pixel dependencies for complete reconstruction in low-texture regions. Additionally, discrete depth layers in occluded environments hinder the cost volume’s ability to model object information effectively. To address these issues, we propose a spatial-aware multi-view stereo network with attention cost volume, termed SA-MVSNet. The network introduces the pixel-driven spatial interaction (PDSI) module, which integrates the hierarchical spatial location enhancement mechanism (HSLE) and the spatial context aggregation mechanism (SCA). Leveraging an efficient parallel architecture, the PDSI module captures pixel-level spatial dependencies with the HSLE and strengthens global contextual information through the SCA. This design improves the network’s ability to represent features in low-texture regions while maintaining high inference efficiency. Furthermore, SA-MVSNet incorporates an attention weight generation branch that refines the cost volume by aggregating multi-scale depth cues, effectively mitigating the impact of occlusion. Experiments on the DTU dataset and the Tanks and Temples dataset show that our method outperforms other learning-based methods, achieving superior performance and strong generalization ability.

With the commercialization of fifth-generation (5G) mobile communication technology and the rapid proliferation of mobile devices (MDs), demand for data computation is surging. This growth increases the reliance of MDs on low latency and high throughput. For this purpose, Mobile Edge Computing (MEC) enhances the user's data processing capability by offloading computation tasks to servers at the network edge. However, achieving high efficiency in task offloading is challenging due to factors such as decision complexity, network dynamics, and user data privacy protection. Additionally, energy causal constraints and the coupling between offloading proportions and resource distribution cannot be ignored. In this paper, we first establish a dynamic task offloading problem to optimize the long-term throughput of the system. Using perturbed Lyapunov optimization, we transform MD delay and energy threshold constraints into the stability control of corresponding virtual queues. Then, we propose the Lyapunov-guided federated deep reinforcement learning (DRL) online task offloading algorithm called LyFOTO, which combines a federated learning (FL) framework and an Actor-Critic (AC) model. Under favorable communication conditions, the LyFOTO algorithm adaptively boosts system throughput; under poorer conditions, it properly delays task offloading, without violating queue backlog constraints. Through mathematical analysis, we discuss the performance of the LyFOTO algorithm. Simulation experiments validate that LyFOTO effectively balances system throughput and device battery energy. Finally, Comparative results show that LyFOTO outperforms other benchmark algorithms in maximizing system throughput while ensuring task backlog and energy threshold constraints.

With the explosive increase of Internet of Things (IoT) devices, an increasing number of computation-intensive applications are emerging in IoT system. However, most IoT devices are limited by size and location, equipped with low-performance CPUs and low-capacity batteries, which cannot go well with computation-intensive applications. Mobile edge computing (MEC) is considered as a promising solution to provide computation-intensive and latency-sensitive services in IoT system, but it is still challenging to improve the throughput and extend the battery life of IoT devices under communication constraints. This paper focuses on the task offloading problem for an MEC system with multiple energy harvesting (EH) devices. To accommodate the system dynamics and ensure the system stability in terms of task queue and battery level, we apply Lyapunov optimization theory, and design a computation tasks maximum offloading algorithm to maximize the system throughput. The algorithm can determine the offloading decision in real-time without knowing any statistical information about the system. We first give a series of mathematical analysis to verify the system stability and discuss the performance of the algorithm. In addition, a number of simulation experiments are conducted to present the efficiency of the algorithm.