High-quality Shapes Research Articles

Study on the preparation and mechanical behavior of carbon fiber reinforced aluminum matrix composites stator blade

The advancement of high-performance stator blades stands as a critical avenue for enhancing the efficacy of aero engines. This study aims to prepare carbon fiber reinforced aluminum matrix (CF/Al) composite stator blades with high-quality shapes and properties, optimize the lay-up design using Fibersim software, and investigate the effect of extrusion temperature on the forming quality. The mechanical properties and damage behavior were systematically analyzed by tensile, compression, and interlaminar shear tests. In addition, the vibration mode simulation reveals the force state under the 1st to 8th-order vibration modes. Results indicate that the [0°/+45°/0°/-45°/90°/-45°/0°/+45°/0°] lay-up parameters were optimal, achieving excellent shape and performance of curved preforms after curing. Composite blades fabricated at an extrusion temperature of 680°C exhibited clear contours, consistent dimensions, and no macro defects. SEM and EDS analyses showed uniform impregnation in all regions of the blade, high density, and good densification. Compared with the matrix alloy, the tensile strength of the composite blade was improved by 64.94%, the compressive strength by 35.7%, and the interlayer shear strength was as low as 72.6 MPa. The vibration mode simulation verified the applicability of the blade in the first-order vibration mode, which provides strong support for the application of composite materials in the aerospace field.

CharacterGen: Efficient 3D Character Generation from Single Images with Multi-View Pose Canonicalization

BNRist, Department of Computer Science and Technology, Tsinghua University, China In the field of digital content creation, generating high-quality 3D characters from single images is challenging, especially given the complexities of various body poses and the issues of self-occlusion and pose ambiguity. In this paper, we present CharacterGen, a framework developed to efficiently generate 3D characters. CharacterGen introduces a streamlined generation pipeline along with an image-conditioned multi-view diffusion model. This model effectively calibrates input poses to a canonical form while retaining key attributes of the input image, thereby addressing the challenges posed by diverse poses. A transformer-based, generalizable sparse-view reconstruction model is the other core component of our approach, facilitating the creation of detailed 3D models from multi-view images. We also adopt a texture-back-projection strategy to produce high-quality texture maps. Additionally, we have curated a dataset of anime characters, rendered in multiple poses and views, to train and evaluate our model. Our approach has been thoroughly evaluated through quantitative and qualitative experiments, showing its proficiency in generating 3D characters with high-quality shapes and textures, ready for downstream applications such as rigging and animation.

BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation

We present BlockFusion, a diffusion-based model that generates 3D scenes as unit blocks and seamlessly incorporates new blocks to extend the scene. BlockFusion is trained using datasets of 3D blocks that are randomly cropped from complete 3D scene meshes. Through per-block fitting, all training blocks are converted into the hybrid neural fields: with a tri-plane containing the geometry features, followed by a Multi-layer Perceptron (MLP) for decoding the signed distance values. A variational auto-encoder is employed to compress the tri-planes into the latent tri-plane space, on which the denoising diffusion process is performed. Diffusion applied to the latent representations allows for high-quality and diverse 3D scene generation. To expand a scene during generation, one needs only to append empty blocks to overlap with the current scene and extrapolate existing latent tri-planes to populate new blocks. The extrapolation is done by conditioning the generation process with the feature samples from the overlapping tri-planes during the denoising iterations. Latent tri-plane extrapolation produces semantically and geometrically meaningful transitions that harmoniously blend with the existing scene. A 2D layout conditioning mechanism is used to control the placement and arrangement of scene elements. Experimental results indicate that BlockFusion is capable of generating diverse, geometrically consistent and unbounded large 3D scenes with unprecedented high-quality shapes in both indoor and outdoor scenarios.

Dissecting the Interplay Mechanism among Process Parameters toward the Biofabrication of High-Quality Shapes in Embedded Bioprinting.

Embedded bioprinting overcomes the barriers associated with the conventional extrusion-based bioprinting process as it enables the direct deposition of bioinks in 3D inside a support bath by providing in situ self-support for deposited bioinks during bioprinting to prevent their collapse and deformation. Embedded bioprinting improves the shape quality of bioprinted constructs made up of soft materials and low-viscosity bioinks, leading to a promising strategy for better anatomical mimicry of tissues or organs. Herein, the interplay mechanism among the printing process parameters toward improved shape quality is critically reviewed. The impact of material properties of the support bath and bioink, printing conditions, cross-linking mechanisms, and post-printing treatment methods, on the printing fidelity, stability, and resolution of the structures is meticulously dissected and thoroughly discussed. Further, the potential scope and applications of this technology in the fields of bioprinting and regenerative medicine are presented. Finally, outstanding challenges and opportunities of embedded bioprinting as well as its promise for fabricating functional solid organs in the future are discussed.

Log-aesthetic curves: Similarity geometry, integrable discretization and variational principles

In this paper, we consider a class of plane curves called log-aesthetic curves and their generalization which are used in computer aided geometric design. In the framework of similarity geometry, those curves are characterized as invariant curves under the integrable flow on plane curves governed by the Burgers equation. They also admit a variational formulation leading to the stationary Burgers equation as the Euler-Lagrange equation. As an application of the formulation, we propose a discretization of these curves and the associated variational principle which preserves the underlying integrable structure. We finally present algorithms for generating discrete log-aesthetic curves for given G1 data based on similarity geometry. Our method is able to generate S-shaped discrete curves with an inflection as well as C-shaped curves according to the boundary condition. The resulting discrete curves are regarded as self-adaptive discretization and thus high-quality even with the small number of points. Through the continuous representation, those discrete curves provide a flexible tool for the generation of high-quality shapes.

DSG-Net: Learning Disentangled Structure and Geometry for 3D Shape Generation

3D shape generation is a fundamental operation in computer graphics. While significant progress has been made, especially with recent deep generative models, it remains a challenge to synthesize high-quality shapes with rich geometric details and complex structures, in a controllable manner. To tackle this, we introduce DSG-Net, a deep neural network that learns a disentangled structured & geometric mesh representation for 3D shapes, where two key aspects of shapes, geometry and structure, are encoded in a synergistic manner to ensure plausibility of the generated shapes, while also being disentangled as much as possible. This supports a range of novel shape generation applications with disentangled control, such as interpolation of structure (geometry) while keeping geometry (structure) unchanged. To achieve this, we simultaneously learn structure and geometry through variational autoencoders (VAEs) in a hierarchical manner for both, with bijective mappings at each level. In this manner, we effectively encode geometry and structure in separate latent spaces, while ensuring their compatibility: the structure is used to guide the geometry and vice versa. At the leaf level, the part geometry is represented using a conditional part VAE, to encode high-quality geometric details, guided by the structure context as the condition. Our method not only supports controllable generation applications, but also produces high-quality synthesized shapes, outperforming state-of-the-art methods.

Automatic generation of the complete vocal tract shape from the sequence of phonemes to be articulated

Articulatory speech synthesis requires generating realistic vocal tract shapes from the sequence of phonemes to be articulated. This work proposes the first model trained from rt-MRI films to automatically predict all of the vocal tract articulators’ contours. The data are the contours tracked in the rt-MRI database recorded for one speaker. Those contours were exploited to train an encoder–decoder network to map the sequence of phonemes and their durations to the exact gestures performed by the speaker. Different from other works, all the individual articulator contours are predicted separately, allowing the investigation of their interactions. We measure four tract variables closely coupled with critical articulators and observe their variations over time. The test demonstrates that our model can produce high-quality shapes of the complete vocal tract with a good correlation between the predicted and the target variables observed in rt-MRI films, even though the tract variables are not included in the optimization procedure.

SP-GAN

We present SP-GAN, a new unsupervised sphere-guided generative model for direct synthesis of 3D shapes in the form of point clouds. Compared with existing models, SP-GAN is able to synthesize diverse and high-quality shapes with fine details and promote controllability for part-aware shape generation and manipulation, yet trainable without any parts annotations. In SP-GAN, we incorporate a global prior (uniform points on a sphere) to spatially guide the generative process and attach a local prior (a random latent code) to each sphere point to provide local details. The key insight in our design is to disentangle the complex 3D shape generation task into a global shape modeling and a local structure adjustment, to ease the learning process and enhance the shape generation quality. Also, our model forms an implicit dense correspondence between the sphere points and points in every generated shape, enabling various forms of structure-aware shape manipulations such as part editing, part-wise shape interpolation, and multi-shape part composition, etc., beyond the existing generative models. Experimental results, which include both visual and quantitative evaluations, demonstrate that our model is able to synthesize diverse point clouds with fine details and less noise, as compared with the state-of-the-art models.

Change detection in images using shape-aware siamese convolutional network

Change detection gradually becomes a core technique due to its wide applications of image or video analysis like land cover analysis and real-time monitoring system. Recently, siamese convolutional networks have been adopted for change detection which demonstrate the state-of-the-art performance. Although most of the previous works have better location accuracy, these methods cannot avoid side effects such as coarse boundaries and empty holes. In this paper, we propose a shape-aware siamese convolutional network (SASCNet) to simultaneously integrate different information for change detection with three steps in an unified network. In the first step, we extract multi-dimension features from paired images and select multi-level change maps generated by a novel siamese encoder–decoder network with multi-scale supervisions. In the second step, we integrate these change maps to obtain complementary information in detail. Finally, we use a residual fine-tune module to refine the predicted change maps and enhance the performance. Because of rich information in different levels and multi-scale supervisions, the predicted change maps could provide precise positioning as well as high-quality shapes. Experimental results on “CDnet 2014 dataset” and “AICD-2012 dataset” show that our method outperforms the state-of-the-art methods in most challenging conditions.

Marbling-based creative modelling

Most mathematical marbling simulations generate patterns for texture mapping and surface decoration. We explore the application of three-dimensional deformations inspired by mathematical marbling as a suite of tools to enable creative shape design. Our tools are expressed as analytical functions of space and are volume-preserving vector fields, meaning that the modelling process preserves volumes and avoids self-intersections. Complicated deformations are easily combined to create complex objects from simple ones. To achieve smooth and high-quality shapes, we also present a mesh refinement and simplification algorithm adapted to our deformations. We show a number of examples of shapes created with our technique in order to demonstrate its power and expressiveness.

Topological sensitivity analysis for three-dimensional linear elasticity problem

In this work we use the Topological-Shape Sensitivity Method to obtain the topological derivative for three-dimensional linear elasticity problems, adopting the total potential energy as cost function and the equilibrium equation as constraint. This method, based on classical shape sensitivity analysis, leads to a systematic procedure to calculate the topological derivative. In particular, firstly we present the mechanical model, later we perform the shape derivative of the corresponding cost function and, finally, we calculate the final expression for the topological derivative using the Topological-Shape Sensitivity Method and results from classical asymptotic analysis around spherical cavities. In order to point out the applicability of the topological derivative in the context of topology optimization problems, we use this information as a descent direction to solve a three-dimensional topology design problem. Furthermore, through this example we also show that the topological derivative together with an appropriate mesh refinement strategy are able to capture high quality shapes even using a very simple topology algorithm.