PG2017short
Permanent URI for this collection
Browse
Browsing PG2017short by Issue Date
Now showing 1 - 7 of 7
Results Per Page
Sort Options
Item Transferring Pose and Augmenting Background Variation for Deep Human Image Parsing(The Eurographics Association, 2017) Kikuchi, Takazumi; Endo, Yuki; Kanamori, Yoshihiro; Hashimoto, Taisuke; Mitani, Jun; Jernej Barbic and Wen-Chieh Lin and Olga Sorkine-HornungHuman parsing is a fundamental task to estimate semantic parts in a human image such as face, arm, leg, hat, and dress. Recent deep-learning based methods have achieved significant improvements, but collecting training datasets of pixel-wise annotations is labor-intensive. In this paper, we propose two solutions to cope with limited dataset. First, to handle various poses, we incorporate a pose estimation network into an end-to-end human parsing network in order to transfer common features across the domains. The pose estimation network can be trained using rich datasets and feed valuable features to the human parsing network. Second, to handle complicated backgrounds, we increase the variations of background images automatically by replacing the original backgrounds of human images with those obtained from large-scale scenery image datasets. While each of the two solutions is versatile and beneficial to human parsing, their combination yields further improvement.Item Adaptive Measurement of Anisotropic Material Appearance(The Eurographics Association, 2017) Vávra, Radomir; Filip, Jiri; Jernej Barbic and Wen-Chieh Lin and Olga Sorkine-HornungWe present a practical adaptive method for acquisition of the anisotropic BRDF. It is based on a sparse adaptive measurement of the complete four-dimensional BRDF space by means of one-dimensional slices which form a sparse four-dimensional structure in the BRDF space and which can be measured by continuous movements of a light source and a sensor. Such a sampling approach is advantageous especially for gonioreflectometer-based measurement devices where the mechanical travel of a light source and a sensor creates a significant time constraint. In order to evaluate our method, we perform adaptive measurements of three materials and we simulate adaptive measurements of ten others. We achieve a four-times lower reconstruction error in comparison with the regular non-adaptive BRDF measurements given the same count of measured samples. Our method is almost twice better than a previous adaptive method, and it requires from two- to five-times less samples to achieve the same results as alternative approaches.Item Robust Edge-Preserved Surface Mesh Polycube Deformation(The Eurographics Association, 2017) Zhao, Hui; Lei, Na; Li, Xuan; Zeng, Peng; Xu, Ke; Gu, Xianfeng; Jernej Barbic and Wen-Chieh Lin and Olga Sorkine-HornungThe problem of polycube construction or deformation is an essential problem in computer graphics. In this paper, we present a robust, simple, efficient and automatic algorithm to deform the meshes of arbitrary shapes into their polycube ones. We derive a clear relationship between a mesh and its corresponding polycube shape. Our algorithm is edge-preserved, and works on surface meshes with or without boundaries. Our algorithm outperforms previous ones in speed, robustness, efficiency. Our method is simple to implement. To demonstrate the robustness and effectiveness of our method, we apply it to hundreds of models of varying complexity and topology. We demonstrate that our method compares favorably to other state-of-the-art polycube deformation methods.Item Pacific Graphics 2017 - Short Papers: Frontmatter(Eurographics Association, 2017) Barbic, Jernej; Lin, Wen-Chieh; Sorkine-Hornung, Olga; Jernej Barbic and Wen-Chieh Lin and Olga Sorkine-HornungItem Computing Restricted Voronoi Diagram on Graphics Hardware(The Eurographics Association, 2017) Han, Jiawei; Yan, Dongming; Wang, Lili; Zhao, Qinping; Jernej Barbic and Wen-Chieh Lin and Olga Sorkine-HornungThe 3D restricted Voronoi diagram (RVD), defined as the intersection of the 3D Voronoi diagram of a pointset with a mesh surface, has many applications in geometry processing. There exist several CPU algorithms for computing RVDs. However, such algorithms still cannot compute RVDs in realtime. In this short paper, we propose an efficient algorithm for computing RVDs on graphics hardware. We demonstrate the robustness and the efficiency of the proposed GPU algorithm by applying it to surface remeshing based on centroidal Voronoi tessellation.Item Real-time Shadow Removal using a Volumetric Skeleton Model in a Front Projection System(The Eurographics Association, 2017) Kim, Jaedong; Seo, Hyunggoog; Cha, Seunghoon; Noh, Junyong; Jernej Barbic and Wen-Chieh Lin and Olga Sorkine-HornungWhen a person is located between a display and a projector in operation, a shadow is cast on the display. The shadow on a display may eliminate important visual information and therefore adversely affects the viewing experiences. There have been various attempts to remove shadows cast on a projection display by using multiple projectors. We propose a real time novel approach to removing shadow cast by the person who dynamically interacts with the display making limb motions in a front projection system. The proposed method utilizes a human skeleton obtained from a depth camera to track the posture of the person which changes over time. A model that consists of spheres and conical frustums is constructed based on the skeleton information in order to represent volumetric information of the person being tracked. Our method precisely estimates the shadow region by projecting the volumetric model onto the display. In addition, employment of intensity masks that is based on a distance field helps suppress the afterimage of shadow that appears when the person moves abrubtly and smooth the difference of the brightness caused by different projectors at the boundary of the shadow region.Item Robust Gas Condensation Simulation with SPH based on Heat Transfer(The Eurographics Association, 2017) Zhang, Taiyou; Shi, Jiajun; Wang, Changbo; Qin, Hong; Li, Chen; Jernej Barbic and Wen-Chieh Lin and Olga Sorkine-HornungMost simulation of natural phenomena in graphics are physically based, oftentimes involving heat transfer, phase transition, environmental constraints, and/or a combination of the above. At the numerical level, the particle-based schemes (e.g., smooth particle hydrodynamics (SPH)) have proved to preserve subtle details while accommodating large quantity of particles and enabling complex interaction during heat transition. In this paper, we propose a novel hybrid complementary framework to faithfully model intricate details in vapor condensation while circumventing disadvantages of the existing methods. The phase transition is governed by robust heat transfer and dynamic characteristic of condensation, so that the condensed drop is precisely simulated by way of the SPH model. We introduce the dew point to ensure faithful visual simulation, as the atmospheric pressure and the relative humidity were isolated from condensation. Moreover, we design a equivalent substitution for ambient impacts to correct the heat transfer across the boundary layer and reduce the quantity of air particles being utilized. To generate plausible high-resolution visual effects, we extend the standard height map with more physical control and construct arbitrary shape of surface via the reproduction on normal map. We demonstrate the advantages of our framework in several fluid scenes, including vapor condensation on a mirror and some more plausible contrasts.