In interpersonal interactions, individuals often exhibit avoidance behaviors toward others they find unpleasant, which can undermine the comfort of everyday social experiences. Existing human-computer interaction (HCI) research has primarily focused on promoting social connections, while support for avoidance-oriented social situations remains underexplored. To address this gap, we propose leveraging Diminished Reality (DR) technology to obscure perceptual cues of undesirable individuals. We designed and implemented a mixed reality prototype system and conducted experiments manipulating both the occlusion method and social distance. Results indicate that DR significantly reduces users’ social anxiety and sense of social presence. Moreover, participants generally expressed positive attitudes toward usage intention and ethical considerations. This work extends HCI research on social comfort, shifting the focus from “facilitating connection” to “supporting avoidance”.

Aggressive driving often triggers anger and retaliatory behaviors, posing threats to traffic safety. This paper proposes an AI-driven apology mechanism based on an Augmented Reality Head-Up Display (AR-HUD), which delivers immediate apologies on behalf of offending drivers during traffic conflicts and repairs damaged social relations through prosocial lies. We conducted a 2 (scenario risk: high vs. low) × 5 (apology depth) mixed-design experiment (N = 40) to evaluate its effectiveness. Results show that AI apologies enhanced positive emotions and forgiveness intentions while reducing anger, with participants also perceiving psychological benefits. These effects were consistent across both high- and low-risk scenarios. Our findings offer a practical design pathway for human-AI emotional regulation in traffic contexts.

Sewing patterns form the structural foundation of the fashion industry, translating 2D conceptual designs into 3D manufacturable garments. With the rise of deep learning, 3D fashion design has seen transformative advancements, automating traditionally labor-intensive processes and enabling intelligent, data-driven workflows. Recent studies have demonstrated promising progress in areas such as sewing pattern generation, reconstruction, and 3D garment modeling. However, to date, no systematic review has specifically examined the integration of deep learning with sewing pattern–driven 3D fashion design. This survey addresses that gap by providing the first comprehensive overview of the field. We propose a novel four-stage pipeline, including representation, generation, reconstruction, and editing, to categorize and analyze current research. Within this pipeline, we review core methodologies, including geometric encoding for pattern representation, data-driven pattern generation, reconstruction from multimodal inputs (e.g., images, sketches, or text), and intuitive 3D garment editing techniques. We also consolidate existing benchmarks, covering both datasets and evaluation metrics, and contextualize the pattern-driven paradigm through comparison with alternative approaches in 2D and pattern-free 3D design. Finally, we identify key challenges, such as limited data availability and the difficulty of incorporating domain-specific design constraints, and outline future research directions to address these issues. By synthesizing current developments and structuring the research landscape, this survey serves as a foundational resource to support and accelerate innovation in manufacturable sewing pattern-driven 3D fashion design.

Generating full-body humans in 360$^{\circ }$∘ has broad applications in digital entertainment, online education and art design. Existing works primarily rely on coarse conditions such as body pose to guide the generation, lacking detailed control over the synthesized results. Regarding this limitation, sketches offer a promising alternative as an expressive condition that enables more explicit and precise control. However, current sketch-based generation methods focus on faces or common objects, how to transfer sketches into 360 $^{\circ }$∘ full-body humans remains unexplored. To bridge this gap, we propose Sketch2Avatar, the first generative model to achieve 3D full-body human generation from hand-drawn sketches. Our model is capable of synthesizing sketch-aligned and 360$^{\circ }$∘-consistent full-body human images by leveraging the geometry information extracted from sketches to guide the 3D representation generation and neural rendering. Specifically, we propose sketchguided 3D representation generation to model the 3D human and maintain the alignment between input sketches and generated humans. Our transformer-based generator incorporates spatial feature guidance and latent modulation derived from sketches to produce high-quality 3D representations. Additionally, our designed bodyaware neural rendering utilizes 3D human body priors from sketches, simplifying the learning of articulated body poses and complex body shapes. To train and evaluate our model, we construct a large-scale dataset comprising approximately 19 K 2D full-body human images and their corresponding sketches in a hand-drawn style. Experimental results demonstrate that our Sketch2Avatar can transfer hand-drawn sketches into photo-realistic 360$^{\circ }$∘ full-body human images with precise sketch-human alignment. Ablation studies further validate the effectiveness of our design choices.

Reconstruction-based methods have demonstrated very promising results for 3D anomaly detection. However, these methods face great challenges in handling high-precision point clouds due to the large scale and complex structure. In this study, a Down-Up Sampling Networks (DUS-Net) is proposed to reconstruct high-precision point clouds for 3D anomaly detection by preserving the group center geometric structure. The DUS-Net first introduces a Noise Generation module to generate noisy patches, which facilitates the diversity of training data and strengthens the feature representation for reconstruction. Then, a Down-sampling Network (Down-Net) is developed to learn an anomaly-free center point cloud from patches with noise injection. Subsequently, an Up-sampling Network (Up-Net) is designed to reconstruct high-precision point clouds by fusing multi-scale up-sampling features. Our method leverages group centers for construction, enabling the preservation of geometric structure and providing a more precise point cloud. Extensive experiments demonstrate the effectiveness of our proposed method, achieving state-of-the-art (SOTA) performance, with an Object-level AUROC of 79.9% and 79.5% and a Point-level AUROC of 71.2% and 84.7% on the Real3D-AD and Anomaly-ShapeNet datasets, respectively.

With the digitalization of automobile cabins, in-vehicle infotainment systems play an increasingly pivotal role in vehicles. This study aims to understand how the interface aesthetics of the in-vehicle infotainment system affect users’ continuance intention in in-vehicle infotainment systems. Based on a literature review, a theoretical model was constructed, encompassing seven latent variables: simplicity, colorfulness, diversity, craftsmanship, functional value, emotional value, and continuance intention. Analysis of 243 valid questionnaires revealed that both functional and emotional values serve as crucial mediators in encouraging users to continue using the in-vehicle infotainment system, with functional quality being the core element. Moreover, simplicity, diversity, and craftsmanship indirectly affect continuance intention by influencing both functional and emotional values. These findings underscore the need for future designers of in-vehicle infotainment systems to focus on interface functionality and emotional needs, and to ensure that content is concise, engaging, user-friendly, and visually polished, thereby enhancing the user experience and fostering the intention to continue usage.

Artificial Intelligence Generated Content (AIGC) has shown significant potential in design, driven by advancements in artificial intelligence technology. However, understanding designers’ willingness to embrace this technology and the factors influencing their decision-making requires further research. In this study, we develop a theoretical model of user behavioral intention in AIGC-assisted design, drawing upon the Diffusion of Innovations theory and the Unified Theory of Acceptance and Use of Technology. Through empirical analysis using the PLS-SEM structural equation model, we investigate the mechanisms behind various influencing factors on behavioral intention. Our findings highlight the relative advantage as the most significant positive factor, emphasizing the importance of the innovation’s benefits in the Diffusion of Innovations theory. Designers prioritize the innovation and assistance provided by AIGC technology in the design process and ideas, recognizing the advantages of the innovation itself over mere performance improvement. This study provides valuable insights into the psychological and behavioral mechanisms guiding designers’ decision-making regarding the application of AIGC technology in design.

Real-time goal collaboration represents a promising approach to human-vehicle cooperative driving; however, it remains underexplored. To address this gap, we introduced an innovative human-vehicle cooperative approach and designed four interactive types with increasing autonomous levels to implement it. Additionally, we proposed seven interface design principles to design three increasing levels of transparency for the four interactive types, aiming to enhance collaboration. Experimental results demonstrate the favorable reception of the proposed cooperative approach by users. Furthermore, higher interactive autonomous levels result in reduced workload, and higher interface transparency levels lead to increased satisfaction, trust, and mutual dependence. Notably, the combination of the highest interactive autonomous level and interface transparency level, which exhibited the best performance, is recommended for practical application. This collaborative approach expands the research domain of human-vehicle cooperative driving and offers extensive potential applications across various relevant scenarios.

In recent studies of 3D shape modelling and reconstruction, the focus has primarily been on the 3D face region. However, accurately creating the entire 3D head opens up a wide range of applications, including headwear design, cranial diagnosis, and avatar design. Therefore, we present our newly developed method of constructing 3D comprehensive morphable models (3DCMM) specifically tailored for human heads, along with a novel 3DCMM-based stepwise pipeline for creating accurate full 3D heads. Within our 3DCMM framework, we constructed a powerful 3D morphable face model with UV-UNet to generate the 3D face and predict the 3D scalp, resulting in a complete representation of the head. Additionally, our 3DCMM-based self-learning approach incorporates novel facial boundary-aware and structure-aware losses for highly accurate overall reconstructions of the entire facial region. Experimental evaluations demonstrate that our 3DCMM exhibits superior face representation power and achieves higher head prediction accuracy than existing models. Consequently, our 3DCMM-based 3D head creation method from a single image demonstrates outstanding performance capability on both face and head benchmarks.

Multi-domain image inpainting utilizes complementary contextual information from auxiliary domain images to restore corrupted regions. While existing methods reconstruct auxiliary images to provide additional guidance, they face fundamental limitations: recovered pixels with complex patterns often lack representative details, while oversimplified patterns offer insufficient contextual information. To address these challenges, we propose HRC-Net, a novel framework incorporating three generative sub-networks for the comprehensive image inpainting task. Our architecture consists of: (1) A Hypothesis Sub-network that enables robust samplings of pixel-wise hypotheses from multi-domain inputs; (2) A Representative Sub-network that learns to score hypothesis quality based on contextual relevance; and (3) a Collaboration Sub-network that optimizes adaptive fusion kernels to integrate the most pertinent details. Together, these components model the joint distribution of representative scores and convolutional kernels, fostering a precise interaction between auxiliary hypotheses and target image corruption to meticulously repair the target image. Extensive evaluations across multiple benchmark datasets demonstrate HRC-Net's superior performance, significantly outperforming state-of-the-art methods in both quantitative metrics and visual quality.

A significant challenge in multi-view clustering lies in the comprehensive extraction of consistency and complementary information from heterogeneous multi-view data. Numerous methods employ contrastive learning techniques to explore the information between views. However, the basic contrastive learning strategy does not consider cluster information when constructing sample pairs, potentially leading to the emergence of false negative pairs (FNPs). To tackle this concern, we propose a Multi-view Subspace Clustering with Consensus Graph Contrastive Learning (CGCL) model. Specifically, a self-representation layer is designed to acquire a consensus graph that elucidates the overall data distribution. Furthermore, a contrastive learning layer utilizes the cluster information embedded in the consensus graph to yield reliable sample pairs, resulting in a reduction of the detrimental FNPs and the extraction of complementary information from the various views. Extensive experiments on public datasets demonstrate the effectiveness of CGCL.

Augmented Reality (AR) has the potential to help drivers become aware of invisible hazards through an Augmented Reality Head-Up Display (AR-HUD). However, this issue is still underexplored. To address it, a novel warning system for invisible dangers in AR-HUD user interfaces has been designed as a carrier for agents' cognitive information to enhance driver perception. This design was created by using a team cooperation perception model that combined the perception cycle of a human driver with a computational agent. Furthermore, user experiments were conducted to investigate the impact of this design on safe driving in two typical scenarios. The experimental results showed that this design can significantly improve drivers’ situation awareness and reaction time in both human-driving and auto-pilot modes, and enhance human drivers' trust in the auto-pilot system. The model and design can be generalized to more AR-HUD scenarios requiring human-machine perception and cognitive cooperation.

Driver’s instinctive responses and skill-based behaviors enable them to react faster and better control their vehicle in dangerous situations. This study incorporated dynamic spatial information design (DSID) in an augmented reality head-up display (AR-HUD) under manual driving conditions. By integrating the skill, rule, and knowledge (SRK) taxonomy and situation awareness (SA) theory, our AR-HUD successfully evoked drivers’ instinctive responses and improved driving safety. First, we converted symbol and sign information processed at the knowledge-based and rule-based levels, respectively, into signal information processed at the skill-based level. Then we developed four AR-HUD interfaces with different dynamic designs for use in a hazardous scenario at an intersection. Finally, we investigated each design’s impact on drivers’ SA and driving performance. Experimental results demonstrated that our DSID enhanced drivers’ SA and accident-avoidance capabilities while reducing their cognitive workload. Among the four AR-HUD interfaces, the one that incorporated all three information elements under study (i.e., lateral warning, dynamic driving space, and speedometer) performed the best. This indicates that our proposed framework has potential applications in other similar dangerous driving scenarios, thus contributing to the development of safer and more efficient driving environments.

As the metaverse develops rapidly, 3D facial age transformation is attracting increasing attention, which may bring many potential benefits to a wide variety of users, e.g., 3D aging figures creation, 3D facial data augmentation and editing. Compared with 2D methods, 3D face aging is an underexplored problem. To fill this gap, we propose a new mesh-to-mesh Wasserstein generative adversarial network (MeshWGAN) with a multi-task gradient penalty to model a continuous bi-directional 3D facial geometric aging process. To the best of our knowledge, this is the first architecture to achieve 3D facial geometric age transformation via real 3D scans. As previous image-to-image translation methods cannot be directly applied to the 3D facial mesh, which is totally different from 2D images, we built a mesh encoder, decoder, and multi-task discriminator to facilitate mesh-to-mesh transformations. To mitigate the lack of 3D datasets containing children's faces, we collected scans from 765 subjects aged 5-17 in combination with existing 3D face databases, which provided a large training dataset. Experiments have shown that our architecture can predict 3D facial aging geometries with better identity preservation and age closeness compared to 3D trivial baselines. We also demonstrated the advantages of our approach via various 3D face-related graphics applications.