We present ClothCombo, a pipeline to drape arbitrary combinations of clothes on 3D human models with varying body shapes and poses. While existing learning-based approaches for draping clothes have shown promising results, multi-layered clothing remains challenging as it is non-trivial to model inter-cloth interaction. To this end, our method utilizes a GNN-based network to efficiently model the interaction between clothes in different layers, thus enabling multi-layered clothing. Specifically, we first create feature embedding for each cloth using a topology-agnostic network. Then, the draping network deforms all clothes to fit the target body shape and pose without considering inter-cloth interaction. Lastly, the untangling network predicts the per-vertex displacements in a way that resolves interpenetration between clothes. In experiments, the proposed model demonstrates strong performance in complex multi-layered scenarios. Being agnostic to cloth topology, our method can be readily used for layered virtual try-on of real clothes in diverse poses and combinations of clothes.

Space planning is one of the popular applications of VR technology including interior design, architecture design, and factory layout. In order to provide easier and efficient methods to accommodate physical objects into virtual space under plan, we suggest applying mixed reality (MR) interface. Our MR system consists of a video see-through display with a touch screen interface, mounted on a mobile platform, and we use screen space 3D manipulations to arrange virtual objects within the MR scene. Investigating the interface with our prototype implementation, we are convinced that our system will help users to design spaces in more easy and effective way.

Visual information has the greatest effect among five senses of human. Therefore, the satisfaction of visual information for representing virtual environments is necessary for good results in information acquisition, virtual training, virtual prototyping, etc. Recently, although there have been a large variety of display systems, there is no such a fully immersive and clearly projected display with high-resolution. In this paper, we describe a hemispherical display which supports a fully immersive experience and high-resolution images. In our display system for generating high-resolution images, a virtual scene image is divided into several pieces those are rendered by a PC cluster and projected with multiple projectors. In this paper, we also describe the PC cluster and projectors designed for optimized performance and a convenient control.

The current paper proposes a font classification method for document images that uses non-negative matrix factorization (NMF), that is able to learn part-based representations of objects. The basic idea of the proposed method is based on the fact that the characteristics of each font are derived from parts of individual characters in each font rather than holistic textures. Spatial localities, parts composing of font images, are automatically extracted using NMF and, then, used as features representing each font. Using hierarchical clustering algorithm, these feature sets are generalized for font classification, resulting in the prototype templates construction. In both the prototype construction and font classification, earth mover's distance (EMD) is used as the distance metric, which is more suitable for the NMF feature space than Cosine or Euclidean distance. In the experimental results, the distribution of features and the appropriateness of the features specifying each font are investigated, and the results are compared with a related algorithm: principal component analysis (PCA). The proposed method is expected to improve the performance of optical character recognition (OCR), document indexing and retrieval systems, when such systems adopt a font classifier as a preprocessor.