Jituo Li

Customizing 3D garments based on volumetric deformation

Improving the reusability of design results is very important for garment design industry, since designing an elegant garment is usually labor-intensive and time-consuming. In this paper, we present a new approach for customizing 3D garment models. Our approach can transfer garment models initially dressed on a reference human model onto a target human model. To achieve this goal, firstly a spatial mapping between the two human models is established with the shape constraints of cross-sections. Secondly, the space around the clothed reference human model is tetrahedralized into five tetrahedral meshes each of which either can be worked dependently with its adjacent ones or can be worked independently. The clothed reference human model is parametrically encoded in the tetrahedral meshes. Thirdly, these tetrahedral meshes are deformed by fitting the reference human model onto the target human model by using constrained volumetric graph Laplacian deformation. The updated garment models are finally decoded from the deformed tetrahedral meshes. As a result, the updated garment models are fitted onto the target human model. Experiments show that our approach performs very well and has the potential to be used in the garment design industry.

Reconstructing 3D human models with a Kinect

Three‐dimensional human model reconstruction has wide applications due to the rapid development of computer vision. The appearance of cheap depth camera, such as Kinect, opens up new horizons for home‐oriented 3D human reconstructions. However, the resolution of Kinect is relatively low, making it difficult to build accurate human models. In this paper, we improve the accuracy of human model reconstruction from two aspects. First, we improve the depth data quality by registering the depth images captured from multi‐views with a single Kinect. The part‐wise registration method and implicit‐surface‐based de‐noising method are proposed. Second, we utilize a statistical human model to iteratively augment and complete the human body information by fitting the statistical human model to the registered depth image. Experimental results and several applications demonstrate the applicability and quality of our system, which can be potentially used in virtual try‐on systems. Copyright

Feature curve-net-based three-dimensional garment customization

Garment customization means that clients can provide their individual information for creating garments that fit them well. It has become a trend in garment industry. Three-dimensional (3D) methods have been emerging and have proved to be intuitive and effective ways for garment customization. In this paper, we propose a novel 3D garment customization approach based on a feature curve-net. A feature curve-net is weaved by feature curves that are initially extracted from 3D human models and then fitted onto 3D garment models. Three-dimensional garment models are locally parameterized on the feature curve-nets by applying bicubic Coons surface technology. Feature curve-nets created from different human models have the same topology connectivity. Thus, garment models on a reference human model can be transferred onto a target human model by reconstructing the garment models from the feature curve-net on the target human model. The shapes of the customized garment models can be further conveniently altered by interactively editing the feature curve-net. Our method supports both the 3D garment resizing and 3D garment editing, while most existing 3D garment customization methods can only support 3D garment resizing. Our method is flexible and can be useful in garment customization.

Optimizing human model reconstruction from RGB-D images based on skin detection

This paper reconstructs human model from multi-view RGB-D images of an Xbox One Kinect. We preprocess the depth images by implicit surface de-noising and then part-wisely register them into a point cloud. A template model is selected from the human model database to fit the registered point cloud of a human body by Laplacian deformation. Skin detection of RGB-D images helps to tightly constrain the skin parts of human body in template fitting step in order to get more precise and lifelike human model. We propose a robust skin detection method that is not affected by clothing pattern and background. Experiments demonstrate the effectiveness of our method.

Predicting detailed body sizes by feature parameters

Purpose – Detailed body sizes are prerequisite for made to measure or customized manufacture. Nowadays, detailed body sizes can be precisely obtained by using 3D scanners, however, the high prices of the scanners block the population for such approaches. The purpose of this paper is to provide an economical and accurate data-driven method which can predict detailed body sizes with a small number of feature sizes. Design/methodology/approach – First, the representative body sizes are extracted from dozens of detail body sizes by using factor analysis and garment knowledge. Among the representative body sizes, those that are easy to be measured are selected as the feature parameters (FPs). Second, by mining the database of the body sizes, mapping from the FPs to the detailed body sizes is expressed by a combination of radial basis function and multiply linear regression. Thus, for an individual human body, his/her detailed body sizes can be predicted by a small number of FPs. Findings – First, FPs which are...

A Unified Cloth Untangling Framework Through Discrete Collision Detection

We present an efficient and stable framework, called Unified Intersection Resolver (UIR), for cloth simulation systems where not only impending collisions but also pre‐existing penetrations often arise. These two types of collisions are handled in a unified manner, by detecting edge‐face intersections first and then forming penetration stencils to be resolved iteratively. A stencil is a quadruple of vertices and it reveals either a vertex‐face or an edge‐edge collision event happened. Each quadruple also implicitly defines a collision normal, through which the four stencil vertices can be relocated, so that the corresponding edge‐face intersection disappear. We deduce three different ways, i.e., from predefined surface orientation, from history data and from global intersection analysis, to determine the collision normals of these stencils robustly. Multiple stencils that constitute a penetration region are processed simultaneously to eliminate penetrations. Cloth trapped in pinched environmental objects can be handled easily within our framework. We highlight its robustness by a number of challenging experiments involving collisions.

Anisotropic Strain Limiting for Quadrilateral and Triangular Cloth Meshes

The cloth simulation systems often suffer from excessive extension on the polygonal mesh, so an additional strain‐limiting process is typically used as a remedy in the simulation pipeline. A cloth model can be discretized as either a quadrilateral mesh or a triangular mesh, and their strains are measured differently. The edge‐based strain‐limiting method for a quadrilateral mesh creates anisotropic behaviour by nature, as discretization usually aligns the edges along the warp and weft directions. We improve this anisotropic technique by replacing the traditionally used equality constraints with inequality ones in the mathematical optimization, and achieve faster convergence. For a triangular mesh, the state‐of‐the‐art technique measures and constrains the strains along the two principal (and constantly changing) directions in a triangle, resulting in an isotropic behaviour which prohibits shearing. Based on the framework of inequality‐constrained optimization, we propose a warp and weft strain‐limiting formulation. This anisotropic model is more appropriate for textile materials that do not exhibit isotropic strain behaviour.

Automatic skinning and animation of skeletal models

In this paper, we present an efficient yet easy-to-implement technique which performs automatic skinning and animation of skeletal models. At a pre-processing stage, a character model is firstly decomposed into a number of segments per bone basis, and each segment is then subdivided into several chunks. A convex cage is automatically created for each chunk. The skinning and animation of skeletal models is achieved via two steps. At the first step, by minimizing a sum of several energy terms, chunk cages are implicitly skinned to the skeleton and animated. These energies are carefully designed to prevent unnatural volume change and guarantee smooth deformation transition between adjacent cages. At the second step, the model mesh vertices, represented as the mean-value coordinates with reference to proper cage vertices, are updated via cage-based deformation technique. Our approach avoids the labor-intensive process of vertex weighting and cage generation. Given the motion of a skeleton, the character model can be animated automatically.

Clothing retrieval based on image bundled features

How to evaluate the similarity between two clothing images is the core technical problem of image based clothing retrieval which is extremely useful in aiding online clothing shopping. According to the characteristics of clothing, we address this issue by computing the similarities between the bundled features of different clothing images. Each bundled feature consists of the point features (SIFT) which are further quantified into local visual words in a maximally stable extremal region (MSER). Researches show that bundled feature becomes much more discriminative than single feature, while the intrinsic geometric constraint of a bundled feature is still defective. In this paper, we add a geometric constraint by SIFTs distance matrix to improve the discriminative power. SIFTs distance matrix is constructed by the distances between every two point features (SIFT) in a bundled feature; it has its merits of scale invariance and rotation invariance. Thus, we can match the bundled features of two clothing images and calculate their similarity. Experimental results based on the clothing image database show that our approach works well in the situations with large clothing deformation, background exchange and part hidden, etc.

Transferring and fitting fixed-sized garments onto bodies of various dimensions and postures

Abstract Many virtual try-on systems involve transferring and fitting garments to bodies of various shapes and postures, with grade preservation. To achieve this goal, garments must be treated as elastic models and their deformation is controlled by the laws of dynamics. Moreover, a collision-free state must be maintained during the simulation, as well as in the final draping state. We present a complete pipeline that concentrates on solving two problems: (1) deforming the target body towards the reference body, and (2) simulating the garment with robust handling of not only impending but also pre-existing collisions. Our solution to the first problem is a skeleton-driven framework, which consists of a collection of techniques, including skeleton embedding, skeleton posture alignment and skeleton-driven mesh deformation. For skeleton posture alignment, we decouple the orientation of each joint into two components: swing and twist, and align them separately. Treating garment models as rigid, the deformed target ‘fits’ into the garments with as few penetrations as possible. When solving the second problem, the body/garment penetrations are untangled along with cloth simulation, so that a collision-free state can be achieved. After that, the deformed target body restores its original shape gradually, while the garments are physically simulated to maintain a collision-free state, until a final draping state is reached on the fully restored target body. Examples show that the proposed framework is effective for garment transfer and fitness evaluation, and can be potentially used in applications like online shopping or customization.