Graphical Models最新文献

Assembling components of man-made objects to create new structures or complete 3D shapes is a popular approach in 3D modeling techniques. Recently, leveraging deep neural networks for assembly-based 3D modeling has been widely studied. However, exploring new component combinations even across different categories is still challenging for most of the deep-learning-based 3D modeling methods. In this paper, we propose a novel generative autoencoder that tackles the component combinations for 3D modeling of man-made objects. We use the segmented input objects to create component volumes that have redundant components and random configurations. By using the input objects and the associated component volumes to train the autoencoder, we can obtain an object volume consisting of components with proper quality and structure as the network output. Such a generative autoencoder can be applied to either multiple object categories for structure hybrid or a single object category for shape completion. We conduct a series of evaluations and experimental results to demonstrate the usability and practicability of our method.

Real time Path-tracing is becoming an important approach for the future of games, digital entertainment, and virtual reality applications that require realism and immersive environments. Among different possible optimizations, denoising Monte Carlo rendered images is necessary in low sampling densities. When dealing with Virtual Reality devices, other possibilities can also be considered, such as foveated rendering techniques. Hence, this work proposes a novel and promising rendering pipeline for denoising a real-time path-traced application in a dual-screen system such as head-mounted display (HMD) devices. Therefore, we leverage characteristics of the foveal vision by computing G-Buffers with the features of the scene and a buffer with the foveated distribution for both left and right screens. Later, we path trace the image within the coordinates buffer generating only a few initial rays per selected pixel, and reconstruct the noisy image output with a novel non-homogeneous denoiser that accounts for the pixel distribution. Our experiments showed that this proposed rendering pipeline could achieve a speedup factor up to 1.35 compared to one without our optimizations.

The emerging remote collaboration in a virtual environment calls for quickly generating high-fidelity 3D humans with cloth from a single image. To estimate clothing geometry and topology, parametric models are widely used but often lack details. Alternative approaches based on implicit functions can generate accurate details but are limited to closed surfaces and may not produce physically correct reconstructions, such as collision-free human avatars. To solve these problems, we present ImplicitPCA, a framework for high-fidelity single-view garment reconstruction that bridges the good ends of explicit and implicit representations. The key is a parametric SDF network that closely couples parametric encoding with implicit functions and thus enjoys the fine details brought by implicit reconstruction while maintaining correct topology with open surfaces. We further introduce a collision-aware regression network to ensure the physical correctness of cloth and human. During inference, an iterative routine is applied to an input image with 2D garment landmarks to obtain optimal parameters by aligning the cloth mesh projection with the 2D landmarks and fitting the parametric implicit fields with the reconstructed cloth SDF. The experiments on the public dataset and in-the-wild images demonstrate that our result outperforms the prior works, reconstructing detailed, topology-correct 3D garments while avoiding garment-body collisions.

Visual analytics combines automated analysis techniques with interactive visualizations for effective understanding, reasoning, and decision-making on complex data. However, accurately classifying sentiments and stances in sentiment analysis remains challenging due to ambiguity and individual differences. This survey examines 35 papers published between 2016 and 2022, identifying unaddressed sources of friction that contribute to a gap between individual sentiment, processed data, and visual representation. We explore the impact of visualizations on data perception, analyze existing techniques, and investigate the many facets of uncertainty in sentiment and stance visualizations. We also discuss the evaluation methods used and present opportunities for future research. Our work addresses a gap in previous surveys by focusing on uncertainty and the visualization of sentiment and stance, providing valuable insights for researchers in graphical models, computational methods, and information visualization.

Segmentation and classification of clothes in real 3D data are particularly challenging due to the extreme variation of their shapes, even among the same cloth category, induced by the underlying human subject. Several data-driven methods try to cope with this problem. Still, they must face the lack of available data to generalize to various real-world instances. For this reason, we present GIM3D plus (Garments In Motion 3D plus), a synthetic dataset of clothed 3D human characters in different poses. A physical simulation of clothes generates the over 5000 3D models in this dataset with different fabrics, sizes, and tightness, using animated human avatars representing different subjects in diverse poses. Our dataset comprises single meshes created to simulate 3D scans, with labels for the separate clothes and the visible body parts. We also provide an evaluation of the use of GIM3D plus as a training set on garment segmentation and classification tasks using state-of-the-art data-driven methods for both meshes and point clouds.

Style transfer is a popular research topic in the field of computer vision. In 3D stylization, a mesh model is deformed to achieve a specific geometric style. We explore a general neural style transfer framework for 3D meshes that can transfer multiple geometric styles from other meshes to the current mesh. Our stylization network is based on a pre-trained MeshNet model, from which content representation and Gram-based style representation are extracted. By constraining the similarity in content and style representation between the generated mesh and two different meshes, our network can generate a deformed mesh with a specific style while maintaining the content of the original mesh. Experiments verify the robustness of the proposed network and show the effectiveness of stylizing multiple models with one dedicated style mesh. We also conduct ablation experiments to analyze the effectiveness of our network.

The goal of digital dress body animation is to produce the most realistic dress body animation possible. Although a method based on the same topology as the body can produce realistic results, it can only be applied to garments with the same topology as the body. Although the generalization-based approach can be extended to different types of garment templates, it still produces effects far from reality. We propose GSNet, a learning-based model that generates realistic garment animations and applies to garment types that do not match the body topology. We encode garment templates and body motions into latent space and use graph convolution to transfer body motion information to garment templates to drive garment motions. Our model considers temporal dependency and provides reliable physical constraints to make the generated animations more realistic. Qualitative and quantitative experiments show that our approach achieves state-of-the-art 3D garment animation performance.

Given a set of generators, the geodesic Voronoi diagram (GVD) defines how the base surface is decomposed into separate regions such that each generator dominates a region in terms of geodesic distance to the generators. Generally speaking, each ordinary bisector point of the GVD is determined by two adjacent generators while each branching point of the GVD is given by at least three generators. When there are sufficiently many generators, straight-line distance serves as an effective alternative of geodesic distance for computing GVDs. However, for a set of sparse generators, one has to use exact or approximate geodesic distance instead, which requires a high computational cost to trace the bisectors and the branching points. We observe that it is easier to infer the branching points by stretching the ordinary segments than competing between wavefronts from different directions. Based on the observation, we develop an unfolding technique to compute the ordinary points of the GVD, as well as a growth-based technique to stretch the traced bisector segments such that they finally grow into a complete GVD. Experimental results show that our algorithm runs 3 times as fast as the state-of-the-art method at the same accuracy level.

Point cloud upsampling has been extensively studied, however, the existing approaches suffer from the losing of structural information due to neglect of spatial dependencies between points. In this work, we propose PU-GAT, a novel 3D point cloud upsampling method that leverages graph attention networks to learn structural information over the baselines. Specifically, we first design a local–global feature extraction unit by combining spatial information and position encoding to mine the local spatial inter-dependencies across point features. Then, we construct an up-down-up feature expansion unit, which uses graph attention and GCN to enhance the ability of capturing local structure information. Extensive experiments on synthetic and real data have shown that our method achieves superior performance against previous methods quantitatively and qualitatively.