Lei Yang

Efficient point cloud compression (PCC) is essential for immersive 3D applications, such as 3D telepresence and remote collaboration, requiring high visual quality despite limited network bandwidth. However, existing PCC methods often prioritize data fidelity while sacrificing perceptual quality, particularly in low-bitrate scenarios. To address these issues, we innovatively propose GS-PCC, the first coding framework that incorporates 3D Gaussian Splatting (3DGS) for PCC. This approach enables high-quality reconstruction with superior perceptual fidelity and optimized bitrate efficiency. Furthermore, GS-PCC provides a unified compression framework that jointly encodes both geometry and attributes. Experimental results demonstrate that GS-PCC significantly outperforms MPEG G-PCC and Google Draco, offering an integrated and efficient solution for human-centric, bandwidth-constrained 3D applications.

In the metaverse era, point cloud video (PCV) streaming on mobile XR devices is pivotal. While most current methods focus on PCV compression from traditional 3-DoF video services, emerging AI techniques extract vital semantic information, producing content resembling the original. However, these are early-stage and computationally intensive. To enhance the inference efficacy of AI-based approaches, accommodate dynamic environments, and facilitate applicability to metaverse XR devices, we present ISCom, an interest-aware semantic communication scheme for lightweight PCV streaming. ISCom is featured with a region-of-interest (ROI) selection module, a lightweight encoder-decoder training module, and a learning-based scheduler to achieve real-time PCV decoding and rendering on resource-constrained devices. ISCom’s dual-stage ROI selection provides significantly reduces data volume according to real-time interest. The lightweight PCV encoder-decoder training is tailored to resource-constrained devices and adapts to the heterogeneous computing capabilities of devices. Furthermore, We provide a deep reinforcement learning (DRL)-based scheduler to select optimal encoder-decoder model for various devices adaptivelly, considering the dynamic network environments and device computing capabilities. Our extensive experiments demonstrate that ISCom outperforms baselines on mobile devices, achieving a minimum rendering frame rate improvement of 10 FPS and up to 22 FPS. Furthermore, our method significantly reduces memory usage by 41.7% compared to the state-of-the-art AITransfer method. These results highlight the effectiveness of ISCom in enabling lightweight PCV streaming and its potential to improve immersive experiences for emerging metaverse application.

In recent years, sketches have attracted much attention as a form of free media, and at the same time, the automatic coloring task of hand-drawn sketches has become one of the research hotspots in the field of vision. Sketch coloring is a challenging task, mainly due to: a) lack of inherent color information; b) the result of coloring is prone to cross-color and overflow; c) poor controllability of the coloring process. Based on this, we design a unique deep network that combines self-attention mechanism to alleviate this problem in this paper. Specifically, we first use the encoding and decoding structure of U-net to capture the delicate details in the sketch; a unique self-attention module is then integrated to automatically capture key areas of the input sketch, thereby improving color distribution modeling and contextual awareness, enhancing the results of automatic coloring. Experiments on a large-scale anime sketch dataset show that the proposed method exhibits significant performance improvement, capturing delicate details in sketches while maintaining faithful color restoration. In addition, our model also supports guided coloring based on provided clues, which providing users more controllability.

Background: From the life course perspective, the childhood living environment exerts long-term effects on adulthood mental health. This study aims to examine childhood neighborhood quality, peer relationships, and trajectories of depressive symptoms among middle-aged and older Chinese adults...

Compared with comprehensive Q&A communities, vertical Q&A communities have more obvious technical, social, intellectual, marketing and scene characteristics. Based on the theory of planning behaviour and the technology acceptance model, a structural equation model of users' willingness to use is constructed by taking tourism Q&A communities as an example, which is helpful to understand the influence mechanism of users' attitude and willingness to use in vertical Q&A communities, and then improve the quality of community knowledge and improve the difficulties of community business operation. This study proves that the users' perceived usefulness, usage attitude, subjective behaviour norms and perceived behaviour control have a positive and significant impact on usage intention. At the same time, ease of use, perceived usefulness and attitude of use have indirect mediating effect on the influence path of intention to use. Finally, the research puts forward some suggestions to improve the sustainable use intention of tourism Q&A community users from the aspects of improving the quality of content, encouraging the production and dissemination of high-quality content, strengthening social attributes, improving community identity, and mining community value.

\textit{Visible Thermal Person Re-Identification} (VTReID) is a cross-modality retrieval problem in computer vision. Accurate VTReID is very challenging due to large modality discrepancies. In this work, we design a novel \textit{Multi-Patch Matching Network} (MPMN) framework to simultaneously mitigate the heterogeneity of coarse-grained and fine-grained visual semantics. In view of cross-modality matching, we verify that aligning modality distributions of the original features is likely to suffer from the selective alignment behavior, \ie, only focuses on easiest dimensions or subspaces. Inspired by adversarial learning, we propose a new \textit{Multi-Patch Modality Alignment} (MPMA) loss to jointly balance and reduce the modality discrepancies of multi-patch features by mining hard subspaces and abandoning easy subspaces. Since multi-patch features are potentially complementary to each other, the semantic correlations between different patches should be exploited during training. Motivated by knowledge distillation, we put forward a new \textit{Cross-Patch Correlation Distillation} (CPCD) loss to transfer the semantic knowledges across different patches. To balance multi-patch tasks, an effective \textit{Patch-Aware Priority Attention} (PAPA) method is further introduced to dynamically prioritize hard patch tasks during training. This paper experimentally demonstrates the effectiveness of the proposed methods, achieving superior performance over the state-of-the-art methods on RegDB and SYSU-MM01 datasets.