Methods that use neural networks for synthesizing 3D shapes in the form of a part-based representation have been introduced over the last few years. These methods represent shapes as a graph or hierarchy of parts and enable a variety of applications such as shape sampling and reconstruction. However, current methods do not allow easily regenerating individual shape parts according to user preferences. In this paper, we investigate techniques that allow the user to generate multiple, diverse suggestions for individual parts. Specifically, we experiment with multimodal deep generative models that allow sampling diverse suggestions for shape parts and focus on models which have not been considered in previous work on shape synthesis. To provide a comparative study of these techniques, we introduce a method for synthesizing 3D shapes in a part-based representation and evaluate all the part suggestion techniques within this synthesis method. In our method, which is inspired by previous work, shapes are represented as a set of parts in the form of implicit functions which are then positioned in space to form the final shape. Synthesis in this representation is enabled by a neural network architecture based on an implicit decoder and a spatial transformer. We compare the various multimodal generative models by evaluating their performance in generating part suggestions. Our contribution is to show with qualitative and quantitative evaluations which of the new techniques for multimodal part generation perform the best and that a synthesis method based on the top-performing techniques allows the user to more finely control the parts that are generated in the 3D shapes while maintaining high shape fidelity when reconstructing shapes.

Neural implicit surface representations have recently emerged as popular alternative to explicit 3D object encodings, such as polygonal meshes, tabulated points, or voxels. While significant work has improved the geometric fidelity of these representations, much less attention is given to their final appearance. Traditional explicit object representations commonly couple the 3D shape data with auxiliary surface-mapped image data, such as diffuse color textures and fine-scale geometric details in normal maps that typically require a mapping of the 3D surface onto a plane, i.e., a surface parameterization; implicit representations, on the other hand, cannot be easily textured due to lack of configurable surface parameterization. Inspired by this digital content authoring methodology, we design a neural network architecture that implicitly encodes the underlying surface parameterization suitable for appearance data. As such, our model remains compatible with existing mesh-based digital content with appearance data. Motivated by recent work that overfits compact networks to individual 3D objects, we present a new weight-encoded neural implicit representation that extends the capability of neural implicit surfaces to enable various common and important applications of texture mapping. Our method outperforms reasonable baselines and state-of-the-art alternatives.

Breast cancer continues to be a prominent contributor to female mortality. Ultrasound imaging stands as a widely utilized technique for detecting breast abnormalities. In this paper, we introduce a novel two-stage neural network model to classify breast cancer in ultrasound images. In the first stage, we employ a fully convolutional network (FCN) to perform image segmentation. The FCN learns to predict segmentation masks from the breast ultrasound images, delineating tumor regions. Subsequently, the second stage involves a convolutional neural network (CNN) to classify tumor type, leveraging tumor masks generated by the first stage and the original ultrasound images. Results showcase the added value of the two-stage approach, with our proposed model achieving a classification accuracy of 92.41 %, consistently surpassing the performance of baseline models that rely solely on CNNs for breast ultrasound image classification.

We introduce a modeling tool which can evolve a set of 3D objects in a functionality-aware manner. Our goal is for the evolution to generate large and diverse sets of plausible 3D objects for data augmentation, constrained modeling, as well as open-ended exploration to possibly inspire new designs. Starting with an initial population of 3D objects belonging to one or more functional categories, we evolve the shapes through part recombination to produce generations of hybrids or crossbreeds between parents from the heterogeneous shape collection. Evolutionary selection of offsprings is guided both by a functional plausibility score derived from functionality analysis of shapes in the initial population and user preference, as in a design gallery. Since cross-category hybridization may result in offsprings not belonging to any of the known functional categories, we develop a means for functionality partial matching to evaluate functional plausibility on partial shapes. We show a variety of plausible hybrid shapes generated by our functionality-aware model evolution, which can complement existing datasets as training data and boost the performance of contemporary data-driven segmentation schemes, especially in challenging cases. Our tool supports constrained modeling, allowing users to restrict or steer the model evolution with functionality labels. At the same time, unexpected yet functional object prototypes can emerge during open-ended exploration owing to structure breaking when evolving a heterogeneous collection.

We introduce an approach to incorporate user guidance into shape generation approaches based on deep networks. Generative networks such as autoencoders and generative adversarial networks are trained to encode shapes into latent vectors, effectively learning a latent shape space that can be sampled for generating new shapes. Our main idea is to enable users to explore the shape space with the use of high-level semantic keywords. Specifically, the user inputs a set of keywords that describe the general attributes of the shape to be generated, e.g., "four legs" for a chair. Then, our method maps the keywords to a subspace of the latent space, where the subspace captures the shapes possessing the specified attributes. The user then explores only this subspace to search for shapes that satisfy the design goal, in a process similar to using a parametric shape model. Our exploratory approach allows users to model shapes at a high level without the need for advanced artistic skills, in contrast to existing methods that allow to guide the generation with sketching or partial modeling of a shape. Our technical contribution to enable this exploration-based approach is the introduction of a label regression neural network coupled with shape encoder/decoder networks. The label regression network takes the user-provided keywords and maps them to distributions in the latent space. We show that our method allows users to explore the shape space and generate a variety of shapes with selected high-level attributes.

We introduce a 3D generative shape model based on the generalized autoencoder (GAE). GAEs learn a manifold latent space from data relations explicitly provided during training. In our work, we train a GAE for volumetric shape generation from data similarities derived from the Chamfer distance, and with a loss function which is the combination of the traditional autoencoder loss and the GAE loss. We show that this shape model is able to learn more meaningful structures for the latent manifolds of different categories of shapes, and provides better interpolations between shapes when compared to previous approaches such as autoencoders and variational autoencoders.

In 3D shape modeling, making sure that the modeled shapes are functional can largely facilitate the modeling process, since then the user is able to create more realistic shapes. In this thesis, we present an analysis method for evaluating the functionality of 3D shapes, especially hybrid shapes with multiple functionalities. Our method is based on functionality partial matching, which localizes the functionality analysis down to the partial shape level. We show that functionality partial matching enables functionality analysis for hybrid shapes. Moreover, we incorporate functionality partial matching into an evolutionary shape modeling framework, which evolves an initial set of shapes through crossover operations at the level of shape parts, making the evolutionary process functionality-aware. We show that our functionality-aware model evolution can produce a large and diverse population of functionally plausible hybrid shapes.

To effectively ensure data consistency is a challenge in today's wireless sensor network (WSN) applications. This paper, based on the simplification of traditional transaction processing from database management system (DBMS), puts forward the concepts of update transaction and query transaction within the context of WSNs and proposes a novel transaction processing protocol, the simple transaction commit protocol (STCP), for WSN systems. In STCP, the base station, as coordinator, is responsible for initializing a transaction and broadcasting the transaction to participant nodes. The participants, on the other hand, commit the transaction according to a timer, which enables the participants to send acknowledgment or conflict messages to the base station at a regular time interval. The transactions suspended by conflict are awakened through a triggering mechanism. Compared to the traditional protocols of distributed systems, STCP, which adapts better to the characteristics and requirements of WSNs, can effectively and efficiently ensure data consistency in WSN systems.

针对在几何处理领域有着广泛应用的三角形网格参数化问题,研究了基于重心映射的三角形网格参数化方法.利用geometry-processing-js类库中的半边数据结构,采用均匀拉普拉斯权重、拉普拉斯-贝尔特拉米权重和中值权重三种加权方案,对重心映射法进行了实现,并根据三角形的形变量分析了参数化结果.结果表明:中值权重为重心映射法的最优加权方案.

Affine transformation is a kind of frequently used geometric image transformation in the field of computer image processing. An affine transformation matrix can be used to describe any linear transformation and one kind of nonlinear transformation. It gives an intro-duction to the mathematical principles of affine transformation and makes an analysis of the algorithms of affine transformation basing on the OpenCV function library. If one image is related to another by an affine transformation,three pairs of corresponding points of the two images are needed to solve for the 2í3 affine transformation matrix M ,which is used to apply the transformation to the source image. A series of interpolation algorithms can be employed such as nearest neighbor interpolation,linear interpolation,cubic spline interpolation and Lanczos interpolation to implement the affine transformation. An example is given concerning affine transformation of an image.