Search

Parsing of human images is a fundamental task for determining semantic parts such as the face, arms, and legs, as well as a hat or a dress. Recent deep-learning-based methods have achieved significant improvements, but collecting training datasets with pixel-wise annotations is labor-intensive. In this paper, we propose two solutions to cope with limited datasets. Firstly, to handle various poses, we incorporate a pose estimation network into an end-to-end human-image parsing network, in order to transfer common features across the domains. The pose estimation network can be trained using rich datasets and can feed valuable features to the human-image parsing network. Secondly, to handle complicated backgrounds, we increase the variation in image backgrounds automatically by replacing the original backgrounds of human images with others obtained from large-scale scenery image datasets. Individually, each solution is versatile and beneficial to human-image parsing, while their combination yields further improvement. We demonstrate the effectiveness of our approach through comparisons and various applications such as garment recoloring, garment texture transfer, and visualization for fashion analysis.

Creating a three-dimensional (3D)-printed liver model is costly, and the visibility of the inner structures is slightly hindered. We developed a novel structure that simultaneously solves both of these problems. The outer frames were set up along the liver surface. Our structure did not use the transparent loading material because this material increases the printing cost. Therefore, we were able to directly observe the inside of the structure. We performed hepatectomy using this novel 3D-printed liver model. Using this model, we were able to clearly simulate the resection line and safely perform the surgery. Our process was more cost effective, had a shorter production time, and improved the visibility than other processes. We developed a novel 3D-printed liver for hepatectomy, which made the procedure easier, reduced the production cost, and improved the visibility; this approach may be useful for future surgeries.

We present an interactive system that allows users to design original pop-up cards. A pop-up card is an interesting form of papercraft consisting of folded paper that forms a three-dimensional structure when opened. However, it is very difficult for the average person to design pop-up cards from scratch because it is necessary to understand the mechanism and determine the positions of objects so that pop-up parts do not collide with each other or protrude from the card. In the proposed system, the user interactively sets and edits primitives that are predefined in the system. The system simulates folding and opening of the pop-up card using a mass–spring model that can simply simulate the physical movement of the card. This simulation detects collisions and protrusions and illustrates the movement of the pop-up card. The results of the present study reveal that the user can design a wide range of pop-up cards using the proposed system.

In this paper, we realized an efficient 3D shape retrieval system based on shape alignment and shape orientation analysis. In this system, we suggest extracting the spatial orientation of the polygon surfaces as the feature of one 3D shape. This information is analyzed by multi-resolution wavelet analysis, and the low frequency components are applied to the feature vector. In the preprocessing stage, we adopt four methods of shape alignment including principal component analysis, continuous principal component analysis, normal-based principal component analysis, and plane reflection symmetry analysis (PRSA). We investigated the influence of four alignment methods on retrieval performance. In the orientation sampling stage, the sampling planes are placed on a cube and a dodecahedron, respectively. We also investigated the influence of this two sampling methods on retrieval performance. Finally, one shape descriptor based on plane reflection symmetry analysis and dodecahedron sampling plane (PRSA-DOD) is proposed. We compare this novel shape descriptor, PRSA-DOD descriptor, with the previous methods on Princeton shape benchmark, and results show that this method achieves the higher retrieval performance. This PRSA-DOD descriptor is selected to construct the search engine of system; in the system, the retrieval interface and search engine are implemented.