Cloth Deformation Research Articles

Modeling Realistic Clothing From a Single Image Under Normal Guide.

We propose a robust and highly realistic clothing modeling method to generate a 3D clothing model with visually consistent clothing style and wrinkles distribution from a single RGB image. Notably, this entire process only takes a few seconds. Our high-quality clothing results benefit from the idea of combining learning and optimization, making it highly robust. First, we use the neural networks to predict the normal map, a clothing mask, and a learning-based clothing model from input images. The predicted normal map can effectively capture high-frequency clothing deformation from image observations. Then, by introducing a normal-guided clothing fitting optimization, the normal maps are used to guide the clothing model to generate realistic wrinkles details. Finally, we utilize a clothing collar adjustment strategy to stylize clothing results using predicted clothing masks. An extended multi-view version of the clothing fitting is naturally developed, which can further improve the realism of the clothing without tedious effort. Extensive experiments have proven that our method achieves state-of-the-art clothing geometric accuracy and visual realism. More importantly, it is highly adaptable and robust to in-the-wild images. Further, our method can be easily extended to multi-view inputs to improve realism. In summary, our method can provide a low-cost and user-friendly solution to achieve realistic clothing modeling.

Learning View Synthesis for Desktop Telepresence with Few RGBD Cameras.

Recent telepresence systems have shown significant improvements in quality compared to prior systems. However, they struggle to achieve both low cost and high quality at the same time. In this work, we envision a future where telepresence systems become a commodity and can be installed on typical desktops. To this end, we present a high-quality view synthesis method that uses a cost-effective capture system that consists of commodity hardware accessible to the general public. We propose a neural renderer that uses a few RGBD cameras as input to synthesize novel views of a user and their surroundings. At the core of the renderer is Multi-Layer Point Cloud (MPC), a novel 3D representation that improves reconstruction accuracy by removing non-linear biases in depth cameras. Our temporally-aware renderer further improves the stability of synthesized videos by conditioning on past information. Additionally, we propose Spatial Skip Connections (SSC) to improve image upsampling under limited GPU memory. Experimental results show that our renderer outperforms recent methods in terms of view synthesis quality. Our method generalizes to new users and challenging content (e.g., hand gestures and clothing deformation) without costly per-video optimization, object templates, or heavy pre-processing. The code and dataset will be made available.

CTSN: Predicting cloth deformation for skeleton-based characters with a two-stream skinning network

We present a novel learning method using a two-stream network to predict cloth deformation for skeleton-based characters. The characters processed in our approach are not limited to humans, and can be other targets with skeleton-based representations such as fish or pets. We use a novel network architecture which consists of skeleton-based and mesh-based residual networks to learn the coarse features and wrinkle features forming the overall residual from the template cloth mesh. Our network may be used to predict the deformation for loose or tight-fitting clothing. The memory footprint of our network is low, thereby resulting in reduced computational requirements. In practice, a prediction for a single cloth mesh for a skeleton-based character takes about 7 ms on an nVidia GeForce RTX 3090 GPU. Compared to prior methods, our network can generate finer deformation results with details and wrinkles.

Impact of LWR assembly structural features on cladding burst behavior under LOCA conditions

This provides an initial scoping study on clad balloon and burst behavior for burnup extension of reactor fuel. The associated issues with burnup extension are fuel fragmentation, relocation, and dispersal in the event of cladding failure. The general finding of this work is that the structural features, spacer grids and mixing vanes, locally suppress cladding deformation but have little impact on the overall clad performance during loss-of-coolant accidents. The work detailed in a previous report by Capps et al. focused on core optimization via neutronics, thermal hydraulics and thermomechanical analysis for burnups beyond 62 GWD/tU and enrichments above 5%. Uncertainty of fuel fragmentation relocation and dispersal in high-burnup rods during accident conditions was also investigated. The dispersal aspect of fuel fragmentation depends on cladding rupture. Thus, assessing uncertainties in the rupture behavior is helpful in estimating the dispersal of high-burnup fuel. This study builds on the previous work by assessing the impact of assembly structural features on cladding balloon and burst behavior in a full-length fuel rod.In this work, the BISON fuel performance code was used to generate 2D radial and height meshes containing structural features commonly used in nuclear fuel assemblies. First, meshes were generated with spacer grids. Results were then compared to the cladding burst temperature and balloon strain results from the previous work. A mesh sensitivity study was performed to ensure that mixing vanes and spacer grid effects were appropriately considered, resulting in a more refined mesh than the previous study. The balloon deformation and burst times of the cladding were compared to the original case. Consideration was also given to the effect of rod initial pressure. 3D quarter rod simulations were also performed and found good agreement with the 2D simulations in clad deformation and reasonable agreement in burst times.

Appearance flow estimation for online virtual clothing warping via optimal feature linear assignment

Clothing warping to spatially align source garments with the corresponding body parts is crucial in clothing media tasks such as virtual try-on and pose-guided person generation. Recent pioneering work has utilized flow fields with additional dimensions of freedom to simulate clothing warping flexibly. However, current methods for estimating appearance flow typically rely on calculating just the local cost volume which contains multiple noisy matching points, potentially leading to a mismatch between clothing and body parts. To address this issue, we propose a novel appearance flow estimation network(Warping-Flow) for clothing warping based on optimal features linear assignment. Specially, two remarkable contributions are made to improve feature matching precision. First, a local context feature aggregation module is proposed to enhance the semantic feature distinction of the source cloth and target pose. Second, Warping-Flow estimates a hard attention mask through the cost volume to filter irrelevant features, followed by the optimal linear assignment algorithm to normalize the cost volume to a discrete permutation matrix that explicitly models the most contributing bipartite matches. Experiments conducted on the VITON and VITON-HD datasets demonstrate that Warping-Flow outperforms existing state-of-the-art algorithms, particularly in cases involving complex clothing deformation. Furthermore, Warping-Flow can serve as a plug-in to improve existing garment media technologies.

Assessment of cladding ballooning during DBA-LOCAs with FRAPTRAN

The assessment of cladding degradation mechanisms under anticipated DBA LOCA conditions requires analytical tools capable of properly modelling the processes involved in clad deformation and burst. The present work proves that the deviations found in FRAPTRAN simulations of burst and LOCA tests, mostly concerning time to failure, come to a good extent from the high temperature creep law, whereas failure limits barely play any role in the deviations. According to an analysis conducted with an alternative model, one might conclude that a Norton-type formulation, once extended to irradiated conditions, might substantially enhance FRAPTRAN accuracy. Besides, this work shows how the formulation adopted to estimate plastic strains up to the instability strain also plays an important role in the time-to-failure prediction.

D‐Cloth: Skinning‐based Cloth Dynamic Prediction with a Three‐stage Network

AbstractWe propose a three‐stage network that utilizes a skinning‐based model to accurately predict dynamic cloth deformation. Our approach decomposes cloth deformation into three distinct components: static, coarse dynamic, and wrinkle dynamic components. To capture these components, we train our three‐stage network accordingly. In the first stage, the static component is predicted by constructing a static skinning model that incorporates learned joint increments and skinning weight increments. Then, in the second stage, the coarse dynamic component is added to the static skinning model by incorporating serialized skeleton information. Finally, in the third stage, the mesh sequence stage refines the prediction by incorporating the wrinkle dynamic component using serialized mesh information. We have implemented our network and used it in a Unity game scene, enabling real‐time prediction of cloth dynamics. Our implementation achieves impressive prediction speeds of approximately 3.65ms using an NVIDIA GeForce RTX 3090 GPU and 9.66ms on an Intel i7‐7700 CPU. Compared to SOTA methods, our network excels in accurately capturing fine dynamic cloth deformations.

Self-supervised feature matched virtual try-on

Abstract Virtual try-on is a technology that enables users to preview the effect of wearing a target garment without wearing the actual garment. However, existing image-based virtual try-on methods often require additional human parsing or segmentation operations to generate intermediate representations required for garment deformation and texture fusion. These operations not only increase the computational complexity and memory consumption, but also limit the real-time and portability of virtual try-on. Additionally, inaccurate parsing results can lead to misleading final generated images. To overcome these challenges, we propose a self-supervised feature matched virtual try-on network, which can directly generate high-quality try-on results from human body images and target clothing images without any additional input. Specifically, we design an optical flow warp module, which focuses on the optical flow changes between the person image and the clothing image to achieve accurate clothing alignment and deformation. Furthermore, a feature refine warp module is designed to enhance the features of the extracted optical flow information and the original character segmentation and analysis operations, reducing the influence of background clutter features on the content, and ensuring that the wrinkles and deformation of the replacement clothes are close to the original clothes. The feature match module is developed to calculate the feature matching loss of the converted clothing and the generated results of the teacher network and the student network, and the corresponding knowledge is distilled and passed to the student network to assist in self-supervised training. We conduct experiments on the VITON dataset and show that our model can generate high quality and high resolution, and our proposed method outperforms the state-of-the-art virtual try-on methods both qualitatively and quantitatively.

Nonlinear cloth simulation with isogeometric analysis

AbstractPhysically based cloth simulation with nonlinear behaviors is studied in this article by employing isogeometric analysis (IGA) for the surface deformation in 3D space. State‐of‐the‐art simulation techniques, which primarily rely on the triangular mesh to calculate physical points on the cloth directly, require a large number of degrees of freedom. An effective method for the cloth deformation that employs high‐order continuous B‐spline surfaces dependent on control points is proposed. This method leads to the merit of fewer degrees of freedom and superior smoothness. The deformation gradient on the high‐order IGA element is then represented by the gradient of the B‐spline function. An iterative method for solving the nonlinear optimization transferred from the implicit integration and a direct implicit–explicit method are derived on the basis of elastic force calculation to improve efficiency. The knots of the representation are effectively utilized in collision detection and response to reduce the computational burden. Experiments of nonlinear cloth simulation demonstrate the superiority of the proposed method considering performance and efficiency, achieving accurate, efficient, and stable deformation.

Self-adaptive Clothing Mapping based Virtual Try-on

Virtual Try-ON (VTON), as an innovative visual application in e-commerce scenarios with great commercial value, has been widely studied in recent years. Due to its better robustness and realistic effect, deformation-synthesize based VTON has become the dominant approach in this field. Existing clothing deformation techniques optimize the mapping relations between the original clothing image and the ground truth image of the worn clothing. However, there are color differences between the original and ground truth clothing images caused by lighting, warping and occlusion. The color differences may lead to misaligned clothing mapping by only minimizing the cost of pixel value difference. Another drawback is that taking the parsing prediction as ground truth will bring alignment remnant, rooting in the processing order of parsing and deformation. Aiming above two drawbacks, we put forward the Self-Adaptive clothing Mapping basEd Virtual Try-ON (SAME-VTON) for achieving realistic virtual try-on results as the same as real. The core of SAME-VTON is the self-adaptive clothing mapping technique, composed of two parts: a color-adaptive clothing mapping module and a parsing-adaptive prediction process. In the color-adaptive clothing mapping module, we map each pixel of the target clothing with a combination of multiple pixel values from the original clothing image, which considers both the position and color changes. Furthermore, different combination weights are learned to increase the diversity of color mapping. In the parsing-adaptive prediction process, the color-adaptive clothing mapping module is adopted to deform clothing firstly, then human parsing result is predicted under the reference of the deformed clothing, which can avoid alignment remnant. Extensive experiments demonstrate that the proposed SAME-VTON with self-adaptive clothing mapping technique can achieve optimal mapping in the case of large color differences and obtain superior results compared with existing deformation-synthesize based VTON.

Human-pose estimation based on weak supervision

BackgroundIn computer vision, simultaneously estimating human pose, shape, and clothing is a practical issue in real life, but remains a challenging task owing to the variety of clothing, complexity of deformation, shortage of large-scale datasets, and difficulty in estimating clothing style. MethodsWe propose a multistage weakly supervised method that makes full use of data with less labeled information for learning to estimate human body shape, pose, and clothing deformation. In the first stage, the SMPL human-body model parameters were regressed using the multi-view 2D key points of the human body. Using multi-view information as weakly supervised information can avoid the deep ambiguity problem of a single view, obtain a more accurate human posture, and access supervisory information easily. In the second stage, clothing is represented by a PCAbased model that uses two-dimensional key points of clothing as supervised information to regress the parameters. In the third stage, we predefine an embedding graph for each type of clothing to describe the deformation. Then, the mask information of the clothing is used to further adjust the deformation of the clothing. To facilitate training, we constructed a multi-view synthetic dataset that included BCNet and SURREAL. ResultsThe Experiments show that the accuracy of our method reaches the same level as that of SOTA methods using strong supervision information while only using weakly supervised information. Because this study uses only weakly supervised information, which is much easier to obtain, it has the advantage of utilizing existing data as training data. Experiments on the DeepFashion2 dataset show that our method can make full use of the existing weak supervision information for fine-tuning on a dataset with little supervision information, compared with the strong supervision information that cannot be trained or adjusted owing to the lack of exact annotation information. ConclusionsOur weak supervision method can accurately estimate human body size, pose, and several common types of clothing and overcome the issues of the current shortage of clothing data.

Leveraging 4D Golf Apparel Wear Simulation in Online Shopping: A Promising Approach to Minimizing the Carbon Footprint

As fashion e-commerce grows, the online return rates are running higher than ever before. Online customers buy the same product in multiple sizes or colors with the intention of returning what is not necessary as they are unable to have a tactile experience during their purchase. In terms of sustainability, returns have a huge negative impact on the environment, causing waste sent to landfills and carbon emissions. In the United States alone, over 15 million metric tons of carbon dioxide are annually emitted from transporting returned inventory. This study explored an innovative way to help reduce online returns due to fit and sizing issues using four-dimensional (4D) golf apparel wear simulation. The study observed how online customers reacted to an apparel wear simulation where they could see the body–clothing interactions, such as dynamic changes in the drape of a garment and cloth deformations caused by different body movements, with a focus on golf apparel. Female customers (n = 13) with experience playing golf and purchasing golf apparel online participated in randomized experiments where three different e-commerce demo websites embedded with simulations were shown. In-depth interviews were followed to collect qualitative data, and surveying was used to quantitatively assess the perceived usefulness of 4D golf apparel wear simulations. The findings of the study indicated that the wear simulation has the potential to help customers find the correct fit and size when shopping online. By exploring the idea of providing a more accurate representation of how apparel fits and interacts with the body, this study sheds light on the promising approach of leveraging 4D golf apparel wear simulations in online shopping to enhance sustainable fashion and potentially contribute to reducing the carbon footprint by minimizing returns.

Automatic temporal clothing deformation prediction: applicable to variable shape and motion

Simulating temporal three-dimensional (3D) deformations of clothing worn by the human body is a core technology in computer graphics that plays a vital role in various fields, such as computer games, animation, and movies. Physics-based simulation and data-driven methods are two mainstream technologies used to generate clothing deformation. However, when it is necessary to quickly generate clothing animations of different body shapes and motions, the existing methods cannot balance efficiency and effectiveness. In this paper, we present a learning-based method, given human body shape and motion, which automatically synthesizes temporal 3D deformations of clothing in real-time. A temporal framework based on the transformer is designed to capture the correlation between clothing deformation and shape features of the moving human body, as well as the frame-level dependency. A feature fusion strategy is an innovation used to fuse the two features of shape and motion. We also perform post-processing on the penetration of clothing and the human body, generating collision-free cloth deformation sequences. To evaluate the method, we build a human motion dataset based on the large-scale public human body dataset AMASS, and further develop a clothing deformation dataset. We qualitatively and quantitatively demonstrate that our approach outperforms existing methods in terms of temporal clothing deformation with variable shape and motion, as well as producing realistic deformation at interactive rates.

Deep Reconstruction of 3-D Human Poses From Video

Deep Learning advances have made it possible to recover full 3D meshes of human models from individual images. However, extension of this notion to videos for recovering temporally coherent poses is still under-explored. A major challenge in this direction is the lack of appropriately annotated video data for learning the desired computational models. Existing human pose datasets only provide 2D or 3D skeleton joint annotations, whereas the datasets are also insufficiently recorded in constrained environments. We first contribute a technique to synthesize monocular action videos with rich 3D annotations that are suitable for learning computational models for full mesh 3D human pose recovery. Compared to the existing methods which simply ‘`texture-map’' clothes onto the 3D human pose models, our approach incorporates Physics-based realistic cloth deformations with human body movements. The generated videos cover a large variety of human actions, poses, and visual appearances, while the annotations record accurate human pose dynamics and human body surface information. Our second major contribution is an end-to-end trainable Recurrent Neural Network for full pose mesh recovery from monocular video. Using the proposed video data and a Long-Short-Term-Memory recurrent structure, our network explicitly learns to model the temporal coherence in videos and imposes geometric consistency over the recovered meshes. We establish the effectiveness of the proposed model with quantitative and qualitative analysis using the proposed and benchmark datasets.

Modeling the contact interaction of leather with squeezing rollers

Mathematical models of the shape of roll contact curves and patterns of distribution of contact stresses in the roll module of a leather squeezing machine were developed. It was revealed that the shapes of the roll contact curves depend on the deformation and geometric parameters of leather and cloth, as well as the coefficient of friction between leather and rolls. It was established that normal stresses change from zero at the beginning and end of the roll contact zone to a maximum at the point of maximum deformation of leather located in the compression zone; shear stresses change their signs at the neutral point, which in the drive roll is located in the compression zone.

An Ergonomic Design Process of the Functional Clothing for Yoga Sports

Abstract Reports attribute many physical, psychological and mental benefits to yoga sports. However, when it comes to actual research, yoga clothing has not attracted the same level of attention. The aim of this study, which involved a questionnaire survey, clothing development and clothing performance evaluation, is to propose an ergonomic design process for the design of yoga functional clothing. Results showed that textile material was rated as the most important factor for yoga clothing. The shoulder and the waist-belly regions were considered as the most important areas for yoga clothing. The newly designed clothing prototype was observed to subject significantly lower pressure to the waist under the forward bending pose (p<0.05), but with significantly higher pressure on the buttocks at the posture of the deep knee bending pose (p<0.05). It also resulted in a lower change rate of clothing vertical displacement, especially at the shoulder and waist regions. The newly designed prototype was rated with a significantly lower tightening sensation and pulling sensation during the deep knee bending posture (p<0.05). Results indicate that proper design of yoga clothing structure and selection of fabric material could reduce clothing deformation, pressure on the skin and improve subjective wearing sensations.

Review of cloth modeling and simulation for virtual fitting

Virtual fitting technology is widely used in many fields, such as e-commerce, garment computer-aided design, and film and game production. Cloth modeling and simulation play an important role in virtual fitting. The realism and simulation speed directly affect the user experience and visual appearance. This paper first reviews the history of cloth modeling and simulation methods. Then, it focuses on four perspectives: yarn-structure modeling of the cloth modeling level; multi-resolution grid simulation; the relation between human posture and cloth deformation; and collision problems of the cloth simulation level. Yarn-structure modeling considers a unit cell that incorporates the physical characteristics of the fabric and the fabric structure. A multi-resolution grid can integrate techniques from different research fields and may achieve a breakthrough in cloth modeling. Generative adversarial networks (GANs) have potential for dealing with the relation between human posture and cloth deformation by comparing several typical algorithms with GANs. Solving the collision and friction problem depends on choosing the right envelope box for refining the human body surface. Finally, the paper concludes with an analysis of future research trends that could improve the fidelity and speed of a simulation. The paper may serve as a reference for research into cloth modeling and simulation for virtual fitting.

Detail‐Aware Deep Clothing Animations Infused with Multi‐Source Attributes

AbstractThis paper presents a novel learning‐based clothing deformation method to generate rich and reasonable detailed deformations for garments worn by bodies of various shapes in various animations. In contrast to existing learning‐based methods, which require numerous trained models for different garment topologies or poses and are unable to easily realize rich details, we use a unified framework to produce high fidelity deformations efficiently and easily. Specifically, we first found that the fit between the garment and the body has an important impact on the degree of folds. We then designed an attribute parser to generate detail‐aware encodings and infused them into the graph neural network, therefore enhancing the discrimination of details under diverse attributes. Furthermore, to achieve better convergence and avoid overly smooth deformations, we proposed to reconstruct output to mitigate the complexity of the learning task. Experimental results show that our proposed deformation method achieves better performance over existing methods in terms of generalization ability and quality of details.

Variational Auto-Encoder for 3D Garment Deformation Prediction

Traditional garment animation workflow relies on the professional clothing simulator, which requires manual editing of artists or animators. There is no doubt that such a process is time-consuming and laborious. Synthesizing garment dynamics according to the input high-level parameters in a semi-automatic way not only helps dismiss the domain gap between inspiration and technical implementation, but also enables artists to focus on the authoring of animating contents. To that end, a variational auto-encoder-based garment animation synthesis method is presented. Firstly, a set of motion sequences composed of different poses are sampled to generate the human body dataset. Secondly, a variational auto-encoder network is constructed to learn the probabilistic distribution of clothing deformation from garment motions under different pose variations. Besides, a mesh Laplacian term on the loss function is introduced to preserve wrinkle details of the synthesized garments. After that, constraints on the latent space are imposed to control the garment shape to be generated. Finally, a refinement process is employed to resolve the penetration between the body surface and garment mesh, obtaining realistic clothing deformations. Proposed method is qualitatively and quantitatively evaluated on the AMASS dataset from different aspects: body motion/shape-driven garment synthesis, garment animation authoring. The experimental results demonstrate that proposed workflow is able to produce visually realistic garments without noticeable artifacts. Proposed method can produce temporally-consistent garment dynamics with shape and pose variations, which assists artists in authoring the desired clothing deformations.

A mortar thermomechanical contact computational framework for nuclear fuel performance simulation

Nuclear fuel performance simulations involve the modeling of complex physical phenomena, ranging from fission gas release to fuel swelling and other temperature-induced effects. For light-water reactors (LWRs), swelling of the fuel and the pressure it imposes on the clad when they come into contact causes permanent clad deformation. Accurately characterizing the fuel-cladding interaction, which involves multiple physics, is essential to accurately simulate the fuel/cladding system. Thermomechanical modeling of this problem using a variationally consistent enforcement (e.g., a mortar approach) has been shown to improve the quality of results and facilitate convergence. Here, we present a general multiphysics computational framework for solving nuclear fuel problems using a mortar approach in BISON, a nuclear fuel performance code. Analyses show that using the mortar approach, which enables variationally consistent constraint enforcement, improves the quality of results as compared to the more commonly used node-on-face enforcement for representative LWR nuclear fuel simulations.