We introduce a new offset meshing method that handles clean 3D surface meshes of arbitrary geometry and topology—where “clean” refers to meshes that are watertight, manifold, and free of self-intersections. Our approach also extends to imperfect, or “dirty,” meshes that violate these conditions, although the problem becomes significantly more difficult in such scenarios, and faithful feature preservation near defective areas cannot always be assured. In contrast to prior techniques, which have largely focused on constant-radius offsets, our method is, to our knowledge, the first to support mitered offsets while effectively preserving sharp features. Our method is designed based on several core principles: (1) explicitly generating the offset vertices and triangles with feature-capturing energy and constraints; (2) prioritizing the generation of the offset geometry before establishing its connectivity, (3) employing exact algorithms in critical pipeline steps for robustness, balancing the use of floating-point computations for efficiency, (4) applying various conservative speed up strategies including early reject non-contributing computations to the final output. Our approach further uniquely supports variable offset distances on input surface elements, offering a wider range of practical applications compared to conventional methods. For benchmarking purposes, we performed an extensive comparison against state-of-the-art offset methods using a curated subset of the Thingi10K dataset. Our results demonstrate the superiority of our approach over current state-of-the-art methods in terms of element count, feature preservation, and non-uniform offset distances of the resulting offset mesh surfaces, marking a significant advancement in the field.

Advanced Deep Neural Networks (DNNs) perform well for high-quality images, but their performance dramatically decreases for degraded images. Data augmentation is commonly used to alleviate this problem, but using too much perturbed data might seriously decrease the performance on pristine images. To tackle this challenge, we take our cue from the assumption of spatial coincidence in human visual perception, i.e. multiscale and varying receptive fields are required for understanding pristine and degraded images. Correspondingly, we propose a novel plug-and-play network architecture, dubbed Quality-Adaptive Receptive Fields (QuARF), to automatically select the optimal receptive fields based on the quality of the input image. To this end, we first design a multi-kernel convolutional block, which comprises multiscale continuous receptive fields. Afterward, we design a quality-adaptive routing network to predict the significance of each kernel, based on the quality features extracted from the input image. In this way, QuARF automatically selects the optimal inference route for each image. To further boost efficiency and effectiveness, the input feature map is split into multiple groups, with each group independently learning its quality-adaptive routing parameters. We apply QuARF to a variety of DNNs and conduct experiments in both discriminative and generation tasks, including semantic segmentation, image translation, and restoration. Thorough experimental results show that QuARF significantly and robustly improves the performance for degraded images, and outperforms data augmentation in most cases.

Volumetric parameterization provides the critical bridge between computer-aided design (CAD) models and Isogeometric Analysis (IGA), where the quality of the parameterization is a primary determinant of computational efficiency and accuracy. Sweeping is a fundamental technique for generating 3D models, and thus, performing volumetric parameterization for sweep-based solids is essential. However, existing sweeping-based parameterization methods are not suitable for multi-axis swept volumes, which are commonly encountered in complex engineering models. To address this limitation, this research introduces an “Decomposition-Parameterization-Recombination” framework. The framework first recursively partitions a complex model into a set of single-axis swept sub-volumes. Subsequently, it generates a high-quality parameterization for each sub-volume by projecting its 3D geometry onto a 2D plane and leveraging frame-field-driven techniques. Finally, through control-point matching and transition zone optimization, these discrete sub-volumes are seamlessly integrated into a globally C0-continuous B-spline volume. Representative case studies validate the proposed framework's capability to effectively generate geometrically accurate volumetric parameterizations for complex multi-axis swept volumes, yielding models that are readily applicable to high-fidelity Isogeometric Analysis.

Visual Emotion Analysis (VEA) seeks to anticipate individuals’ emotional reactions to visual stimuli. The subjective perception of visual emotion is an integrated impact of the appearance, scene, and objects presented in an image. It is thus significance to analysis visual emotion by incorporating diverse visual attributes. Motivated by this, in this paper, we propose a novel VEA method based on Multi-Attribute Joint Reasoning (MAJoR). Specifically, we first use a multi-stream networks to learning multi-attribute representations, including the color, brightness, scene type, and object class of an input image. Afterward, we use a Graph Convolution Network (GCN) to model the inherent relationships among such visual attributes, and to predict the emotion category. Finally, we propose a two-stage knowledge distillation strategy, to boost the performance of light-weight VEA models via MAJoR. Extensive experiments conducted on several VEA databases showcase the superiority of the proposed MAJoR model and the distilled lightweight versions, compared to state-of-the-art approaches. Our code and models are available at: https://github.com/AiArt-Gao/MAJoR.

In this paper, a deep learning framework combined with isogeometric analysis (IGA for short) called IGA-Reuse-Net is proposed for efficient reuse of numerical simulation on a set of topology-consistent models. Compared with previous data-driven numerical simulation methods only for simple computational domains, our method can predict high-accuracy PDE solutions over topology-consistent geometries with complex boundaries. UNet3+ architecture with interlaced sparse self-attention (ISSA) module is used to enhance the performance of the network. In addition, we propose a new loss function that combines a coefficients loss and a numerical solution loss. Several training datasets with topology-consistent models are constructed for the proposed framework. To verify the effectiveness of our approach, two different types of Poisson equations with different source functions are solved on three datasets with different topologies. Our framework can achieve a good trade-off between accuracy and efficiency. It outperforms the physics-informed neural network (PINN for short) model and yields promising results of prediction.