Geometry Sampling-Based Adaption to DCGAN for 3D Face Generation.

Despite progress in the past decades, 3D shape acquisition techniques are still a threshold for various 3D face-based applications and have therefore attracted extensive research. Moreover, advanced 2D data generation models based on deep networks may not be directly applicable to 3D objects because of the different dimensionality of 2D and 3D data. In this work, we propose two novel sampling methods to represent 3D faces as matrix-like structured data that can better fit deep networks, namely (1) a geometric sampling method for the structured representation of 3D faces based on the intersection of iso-geodesic curves and radial curves, and (2) a depth-like map sampling method using the average depth of grid cells on the front surface. The above sampling methods can bridge the gap between unstructured 3D face models and powerful deep networks for an unsupervised generative 3D face model. In particular, the above approaches can obtain the structured representation of 3D faces, which enables us to adapt the 3D faces to the Deep Convolution Generative Adversarial Network (DCGAN) for 3D face generation to obtain better 3D faces with different expressions. We demonstrated the effectiveness of our generative model by producing a large variety of 3D faces with different expressions using the two novel down-sampling methods mentioned above.

Emergency medical rescue efforts after a major earthquake: lessons from the 2008 Wenchuan earthquake.

Major earthquakes often result in incalculable environmental damage, loss of life, and threats to health. Tremendous progress has been made in response to many medical challenges resulting from earthquakes. However, emergency medical rescue is complicated, and great emphasis should be placed on its organisation to achieve the best results. The 2008 Wenchuan earthquake was one of the most devastating disasters in the past 10 years and caused more than 370,000 casualties. The lessons learnt from the medical disaster relief effort and the subsequent knowledge gained about the regulation and capabilities of medical and military back-up teams should be widely disseminated. In this Review we summarise and analyse the emergency medical rescue efforts after the Wenchuan earthquake. Establishment of a national disaster medical response system, an active and effective commanding system, successful coordination between rescue forces and government agencies, effective treatment, a moderate, timely and correct public health response, and long-term psychological support are all crucial to reduce mortality and morbidity and promote overall effectiveness of rescue efforts after a major earthquake.

C3 Assignment: Camera Cubemap Color Assignment for Creative Interior Design.

Color design for 3D indoor scenes is a challenging problem due to many factors that need to be balanced. Although learning from images is a commonly adopted strategy, this strategy may be more suitable for natural scenes in which objects tend to have relatively fixed colors. For interior scenes consisting mostly of man-made objects, creative yet reasonable color assignments are expected. We propose C3 Assignment, a system providing diverse suggestions for interior color design while satisfying general global and local rules including color compatibility, color mood, contrast, and user preference. We extend these constraints from the image domain to [Formula: see text], and formulate 3D interior color design as an optimization problem. The design is accomplished in an omnidirectional manner to ensure a comfortable experience when the inhabitant observes the interior scene from possible positions and directions. We design a surrogate-assisted evolutionary algorithm to efficiently solve the highly nonlinear optimization problem for interactive applications, and investigate the system performance concerning problem complexity, solver convergence, and suggestion diversity. Preliminary user studies have been conducted to validate the rule extension from 2D to 3D and to verify system usability.

AZO-Based ZnO Nanosheet MEMS Sensor with Different Al Concentrations for Enhanced H2S Gas Sensing.

The properties of H2S gas sensing were investigated using a ZnO nanostructure prepared with AZO (zinc oxide with aluminium) and Al surfaces which were developed on a MEMS (Micro Electromechanical System) device. Hydrothermal synthesis was implemented for the deposition of the ZnO nanostructure. To find the optimal conditions for H2S gas sensing, different ZnO growth times and different temperatures were considered and tested, and the results were analysed. At 250 °C and 90 min growth time, a ZnO sensor prepared with AZO and 40 nm Al recorded an 8.5% H2S gas-sensing response at a 200 ppb gas concentration and a 14% sensing response at a gas concentration of 1000 ppb. The dominant sensing response provided the optimal conditions for the ZnO sensor, which were 250 °C temperature and 90 min growth time. Gas sensor selectivity was tested with five different gases (CO, SO2, NO2, NH3 and H2S) and the sensor showed great selectivity towards H2S gas.

Revisiting the Modifiable Areal Unit Problem in Deep Traffic Prediction with Visual Analytics.

Deep learning methods are being increasingly used for urban traffic prediction where spatiotemporal traffic data is aggregated into sequentially organized matrices that are then fed into convolution-based residual neural networks. However, the widely known modifiable areal unit problem within such aggregation processes can lead to perturbations in the network inputs. This issue can significantly destabilize the feature embeddings and the predictions - rendering deep networks much less useful for the experts. This paper approaches this challenge by leveraging unit visualization techniques that enable the investigation of many-to-many relationships between dynamically varied multi-scalar aggregations of urban traffic data and neural network predictions. Through regular exchanges with a domain expert, we design and develop a visual analytics solution that integrates 1) a Bivariate Map equipped with an advanced bivariate colormap to simultaneously depict input traffic and prediction errors across space, 2) a Moran's I Scatterplot that provides local indicators of spatial association analysis, and 3) a Multi-scale Attribution View that arranges non-linear dot plots in a tree layout to promote model analysis and comparison across scales. We evaluate our approach through a series of case studies involving a real-world dataset of Shenzhen taxi trips, and through interviews with domain experts. We observe that geographical scale variations have important impact on prediction performances, and interactive visual exploration of dynamically varying inputs and outputs benefit experts in the development of deep traffic prediction models.

Mesh composition on models with arbitrary boundary topology.

This paper presents a new approach for the mesh composition on models with arbitrary boundary topology. After cutting the needed parts from existing mesh models and putting them into the right pose, an implicit surface is adopted to smoothly interpolate the boundaries of models under composition. An interface is developed to control the shape of the implicit transient surface by using sketches to specify the expected silhouettes. After that, a localized Marching Cubes algorithm is investigated to tessellate the implicit transient surface so that the mesh surface of composed model is generated. Different from existing approaches in which the models under composition are required to have pairwise merging boundaries, the framework developed based on our techniques have the new function to fuse models with arbitrary boundary topology.

A Neuro-Musculo-Skeletal Model for Insects With Data-driven Optimization.

Simulating the locomotion of insects is beneficial to many areas such as experimental biology, computer animation and robotics. This work proposes a neuro-musculo-skeletal model, which integrates the biological inspirations from real insects and reproduces the gait pattern on virtual insects. The neural system is a network of spiking neurons, whose spiking patterns are controlled by the input currents. The spiking pattern provides a uniform representation of sensory information, high-level commands and control strategy. The muscle models are designed following the characteristic Hill-type muscle with customized force-length and force-velocity relationships. The model parameters, including both the neural and muscular components, are optimized via an approach of evolutionary optimization, with the data captured from real insects. The results show that the simulated gait pattern, including joint trajectories, matches the experimental data collected from real ants walking in the free mode. The simulated character is capable of moving at different directions and traversing uneven terrains.

A Sketching Interface for Sitting Pose Design in the Virtual Environment.

Character pose design is one of the most fundamental processes in computer graphics authoring. Although there are many research efforts in this field, most existing design tools consider only character body structure, rather than its interaction with the environment. This paper presents an intuitive sketching interface that allows the user to interactively place a 3D human character in a sitting position on a chair. Within our framework, the user sketches the target pose as a 2D stick figure and attaches the selected joints to the environment (e.g., the feet on the ground) with a pin tool. As reconstructing the 3D pose from a 2D stick figure is an ill-posed problem due to many possible solutions, the key idea in our paper is to reduce solution space by considering the interaction between the character and environment and adding physics constraints, such as balance and collision. Further, we formulated this reconstruction into a nonlinear optimization problem and solved it via the genetic algorithm (GA) and the quasi-Newton solver. With the GPU implementation, our system is able to generate the physically correct and visually pleasing pose at an interactive speed. The promising experimental results and user study demonstrates the efficacy of our method.