We describe a technique to recover depth from a light field (LF) using two proposed features of the LF focal stack. One feature is the property that non-occluding pixels exhibit symmetry along the focal depth dimension centered at the in-focus slice. The other is a data consistency measure based on analysis-by-synthesis, i.e., the difference between the synthesized focal stack given the hypothesized depth map and that from the LF. These terms are used in an iterative optimization framework to extract scene depth. Experimental results on real Lytro and Raytrix data demonstrate that our technique outperforms state-of-the-art solutions and is significantly more robust to noise and undersampling.

No abstract

Exploiting fine-grained semantic features on point cloud data is still challenging because of its irregular and sparse structure in a non-Euclidean space. In order to represent the local feature for each central point that is helpful towards better contextual learning, a max pooling operation is often used to highlight the most important feature in the local region. However, all other geometric local correlations between each central point and corresponding neighbourhood are ignored during the max pooling operation. To this end, the attention mechanism is promising in capturing node representation on graph-based data by attending over all the neighbouring nodes. In this paper, we propose a novel neural network for point cloud analysis, GAPointNet, which is able to learn local geometric representations by embedding graph attention mechanism within stacked Multi-Layer-Perceptron (MLP) layers. Specifically, we highlight different attention weights on the neighbourhood of each center point to efficiently exploit local features. We also combine attention features with local signature features generated by our attention pooling to fully extract local geometric structures and enhance the network robustness. The proposed GAPointNet architecture is tested on various benchmark datasets (i.e. ModelNet40, ShapeNet part, S3DIS, KITTI) and achieves state-of-the-art performance in both the shape classification and segmentation tasks.

The results from this pilot study indicate that monocular usage of a solution of 1% atropine sulfate is an effective treatment to reduce anisometropia, although with some tolerable side effects. Nevertheless, an attenuated benefit was observed after cessation of atropine treatment. Thus, participants should be informed of a possible rebound effect before the administration of atropine for myopic anisometropia.

No abstract

This paper presents a useful and practical procurement approach using the joint replenishment and channel coordination (JR-CC) policy in a two-echelon supply chain considering the coordination cost. The objective is to determine a basic replenishment cycle time and the replenishment interval to minimize the total cost of the supply chain. To solve this NP-hard problem, a simple and improved differential evolution algorithm (IDE) is developed. The performance of the IDE is verified by benchmark functions. Moreover, results of comparative numerical example show the effectiveness of the proposed IDE. IDE can be used as a good candidate for the JR-CC model. Results of numerical examples also indicate that the JR-CC policy can result in considerable cost saving, and enhance the efficiency of a supply chain. But not all members in the supply chain can benefit a lot using this policy. Moreover, results of sensitivity analysis show that retailers have more willingness to adopt the JR-CC policy than the manufacturers because of the different cost savings.

When localizing and detecting 3D objects for autonomous driving scenes, obtaining information from multiple sensors (e.g., camera, LIDAR) is capable of mutually offering useful complementary information to enhance the robustness of 3D detectors. In this paper, a deep neural network architecture, named RoIFusion, is proposed to efficiently fuse the multi-modality features for 3D object detection by leveraging the advantages of LIDAR and camera sensors. In order to achieve this task, instead of densely combining the point-wise feature of the point cloud with the related pixel features, our fusion method novelly aggregates a small set of 3D Region of Interests (RoIs) in the point clouds with the corresponding 2D RoIs in the images, which are beneficial for reducing the computation cost and avoiding the viewpoint misalignment during the feature aggregation from different sensors. Finally, Extensive experiments are performed on the KITTI 3D object detection challenging benchmark to show the effectiveness of our fusion method and demonstrate that our deep fusion approach achieves state-of-the-art performance.

SUMMARYMulti-hypothesis prediction technique, which exploits inter-frame correlation efficiently, is widely used in block-based distributed compressive video sensing. To solve the problem of inaccurate prediction in multi-hypothesis prediction technique at a low sampling rate and enhance the reconstruction quality of non-key frames, we present a resamplebased hybrid multi-hypothesis scheme for block-based distributed compressive video sensing. The innovations in this paper include: (1) multihypothesis reconstruction based on measurements reorganization (MR-MH) which integrates side information into the original measurements; (2) hybrid multi-hypothesis (H-MH) reconstruction which mixes multiple multi-hypothesis reconstructions adaptively by resampling each reconstruction. Experimental results show that the proposed scheme outperforms the state-of-the-art technique at the same low sampling rate.