Search

Densely sampled light fields (LFs) are critical for their further applications, such as digital refocus and depth estimation. However, it is costly and time-consuming to capture them. LF reconstruction, which aims at reconstructing a densely sampled LF from a sparsely sampled one, has attracted extensive attention of researchers. Although existing methods have achieved significant progress, these methods synthesize novel views, either through depth estimation and image warping, which depend heavily on the accuracy of the depth maps and are prone to cause artifacts at occluded regions, or by stacking multi-layer convolutions to learn the inherent structure of the LF, which will result in blurring results due to limited receptive fields when processing scenes with large disparities. We propose a transformer-based neural network for LF reconstruction (termed as LFRTR). Specifically, two novel transformers are introduced, namely angular transformer and spatial transformer. The former can fully explore angular information and correlations among different views, whereas the latter can capture local and non-local spatial texture information within each view. Moreover, dense skip connections are employed to enhance information flow between different layers. Thanks to the inherent global modeling ability of self-attention, the proposed LFRTR can reconstruct high-quality densely sampled LF in complex scenarios, such as large disparity, occlusion, and reflection. Experimental results on both synthetic and real-world LF datasets show that the proposed LFRTR outperforms other state-of-the-art methods in terms of both visual and numerical evaluations. [ABSTRACT FROM AUTHOR]

With the recent rapid development of cities, the dynamics of urban road-traffic commuting are becoming more and more complex. In this research, we study urban road-traffic commuting dynamics based on clustering analysis and a new proposed urban commuting electrostatics model. As a case study, we investigate the characteristics of urban road-traffic commuting dynamics during the morning rush hour in Beijing, China, using over 1.3 million Global Positioning System (GPS) data records of vehicle trajectories. The hotspot clusters are identified using clustering analysis, after which the urban commuting electric field is simulated based on an urban commuting electrostatics model. The results show that the areas with high electric field intensity tend to have slow traffic, and also that the vehicles in most areas tend to head in the same direction as the electric field. The results above verify the validity of the model, in that the electric field intensity can reflect the traffic pressure of an area, and that the direction of the electric field can reflect the traffic direction in that area. This new proposed urban commuting electrostatics model helps greatly in understanding urban road-traffic commuting dynamics and has broad applicability for the optimization of urban and traffic system planning. [ABSTRACT FROM AUTHOR]