Virtual Reality Intelligent Hardware最新文献_第2页

Feed-forward 3D reconstruction with point-cloud representations: From DUSt3R to VGGT and beyond 前馈三维重建与点云表示：从DUSt3R到VGGT和超越

IF 6.1

Virtual Reality Intelligent Hardware Pub Date : 2026-06-01 Epub Date: 2026-07-09 DOI: 10.1016/j.vrih.2026.03.005

Zeyi ZHENG, Xiong YANG, Ran YI, Lizhuang MA

{"title":"Feed-forward 3D reconstruction with point-cloud representations: From DUSt3R to VGGT and beyond","authors":"Zeyi ZHENG, Xiong YANG, Ran YI, Lizhuang MA","doi":"10.1016/j.vrih.2026.03.005","DOIUrl":"10.1016/j.vrih.2026.03.005","url":null,"abstract":"<div><div>This survey reviews feed-forward, point-cloud 3D reconstruction methods from DUSt3R to VGGT and their recent variants. Here, feed-forward primarily refers to predicting dense geometry and, when applicable, camera poses through learned network inference, without relying on classical per-scene SfM + MVS optimization as the main inference mechanism. We first formalize the reconstruction task in pose-aware and pose-free settings, and contrast feed-forward point-map regression with classical Structure-from-Motion and Multi-View Stereo pipelines. Building on this, we organize existing methods into three stages: early pairwise models typified by DUSt3R, DUSt3R-style extensions that enhance multi-view consistency, streaming, efficiency, and dynamic-scene handling, and large unified transformers such as VGGT that process tens to hundreds of views jointly, while noting differences in their inference paradigms. We analyze these models along shared axes, including scene representation, correspondence reasoning, pose regression, fusion strategies, and the role of large-scale training data. We summarize widely used 3D datasets and evaluation metrics, and provide a case study on the DTU benchmark for multi-view depth and point map estimation, highlighting accuracy-efficiency trade-offs between optimization-based and feed-forward approaches. Finally, we discuss open challenges in data scarcity, sparse-view reconstruction, non-Lambertian structures, dynamic scenes, long-context processing, and resource-efficient deployment, and outline future directions that combine feed-forward architectures with differentiable rendering, generative priors, and safety mechanisms to enable scalable and trustworthy 3D reconstruction systems.</div></div>","PeriodicalId":33538,"journal":{"name":"Virtual Reality Intelligent Hardware","volume":"8 3","pages":"Pages 265-282"},"PeriodicalIF":6.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148531495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-process thermodynamic graph learning for 2D fluid simulation 二维流体模拟的多过程热力学图学习

IF 6.1

Virtual Reality Intelligent Hardware Pub Date : 2026-06-01 Epub Date: 2026-07-09 DOI: 10.1016/j.vrih.2026.02.002

Yidi WANG, Aik Beng NG, Simon SEE, Zhengkui WANG, Frank GUAN

{"title":"Multi-process thermodynamic graph learning for 2D fluid simulation","authors":"Yidi WANG, Aik Beng NG, Simon SEE, Zhengkui WANG, Frank GUAN","doi":"10.1016/j.vrih.2026.02.002","DOIUrl":"10.1016/j.vrih.2026.02.002","url":null,"abstract":"<div><div>Solving partial differential equations (PDEs) for fluid simulation is computationally expensive, especially when dealing with complex geometries and high-resolution meshes. Recent advances in physics-informed graph neural networks (PIGNNs) have demonstrated potential in approximating such simulations more efficiently. Particularly, thermodynamic informed graph neural networks (TIGNNs) offer a promising data-driven alternative to traditional PDE solvers for fluid simulations. However, existing TIGNN implementations suffer from significant training inefficiencies, requiring prolonged runtimes and high memory consumption due to the need to maintain large parameter matrices in GPU memory. Inspired by multi-processor strategies in deformable solid simulations, we propose a novel multi-processor thermodynamic-informed graph neural network (MP-TIGNN) architecture to significantly accelerate training without compromising accuracy. Our approach enables faster convergence and reduces memory usage with mixed-precision training by leveraging fully sharded data parallelism (FSDP) across multiple GPUs. Experimental results show that our approach reduces training time by approximately 70% compared to the original setup while maintaining similar prediction accuracy.</div></div>","PeriodicalId":33538,"journal":{"name":"Virtual Reality Intelligent Hardware","volume":"8 3","pages":"Pages 330-346"},"PeriodicalIF":6.1,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148531496","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Adaptive regional segmentation and fitting-based building LOD reconstruction method 基于自适应区域分割和拟合的建筑LOD重建方法

Virtual Reality Intelligent Hardware Pub Date : 2026-04-01 Epub Date: 2026-05-11 DOI: 10.1016/j.vrih.2026.01.004

Bowen LI, Xukun SHEN, Yong HU

{"title":"Adaptive regional segmentation and fitting-based building LOD reconstruction method","authors":"Bowen LI, Xukun SHEN, Yong HU","doi":"10.1016/j.vrih.2026.01.004","DOIUrl":"10.1016/j.vrih.2026.01.004","url":null,"abstract":"<div><div>Reconstructing accurate urban building models remains challenging because of large-scale variability and complex topologies. We introduce a practical multi-step framework that reconstructs a single building from a dense triangular mesh by explicitly exploiting its block-wise composition. The pipeline first partitioned the mesh into spatially coherent regions, then extracted height-aware contours, and classified the geometry into facades, roofs, and appurtenances. For each part, we performed contour-guided vectorized modeling with profile fitting and consistency constraints, producing watertight, semantically structured models at the level of detail (LOD) 2.3. The interactive refinement module further supported user adjustments to resolve rare failures and enforced design regularity. The proposed decomposition and layered fitting yielded compact outputs while preserving the salient geometry and made the reconstruction robust across scales and moderate noise. We also analyzed the modeling assumptions and implementation details to ensure reproducibility. Overall, this study offers a component-aware, engineering-ready solution for converting unstructured meshes into structured building models that are amenable to downstream urban modeling and visualization.</div></div>","PeriodicalId":33538,"journal":{"name":"Virtual Reality Intelligent Hardware","volume":"8 2","pages":"Pages 202-218"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147865369","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

From embodied AI to cobodied AI: Foundations and frontiers 从实体人工智能到实体人工智能：基础和前沿

Virtual Reality Intelligent Hardware Pub Date : 2026-04-01 Epub Date: 2026-05-11 DOI: 10.1016/j.vrih.2026.03.001

Feng LU, Ruijia PANG, Bosong QI, Qinping ZHAO

{"title":"From embodied AI to cobodied AI: Foundations and frontiers","authors":"Feng LU, Ruijia PANG, Bosong QI, Qinping ZHAO","doi":"10.1016/j.vrih.2026.03.001","DOIUrl":"10.1016/j.vrih.2026.03.001","url":null,"abstract":"<div><div>This paper presents a systematic review and technical revisit of recent developments in embodied AI. We comprehensively synthesize current dominant paradigms, representative architectures, and pivotal advancements around five core modules: (1) perception and understanding, (2) reasoning and decision making, (3) control and action, (4) modeling and learning (e.g., VLA (vision-language-action) and WM (world models)), and (5) data and simulation. This analysis establishes a structured and cutting-edge panoramic view of embodied AI technology. Building on this foundation, we explore the transition from embodied AI to a new paradigm of deep human-AI collaboration. Anchored in the original concept of cobodied AI, we adopt a human-centered technical perspective to systematically investigate this paradigm shift. Specifically, we discuss breakthroughs in critical dimensions such as perceptual alignment, collaborative decision-making, action guidance, and bidirectional mutual learning. These efforts aim to realize three core characteristics: human-centered egocentric grounding, dual-mode cognitive integration, and physical co-embodiment. To our knowledge, this work constitutes the first systematic construction of a technical framework and implementation roadmap for realizing cobodied AI, building upon advances in embodied AI but fundamentally reorienting intelligence around the human body and intent, providing a foundational reference for future research in this domain.</div></div>","PeriodicalId":33538,"journal":{"name":"Virtual Reality Intelligent Hardware","volume":"8 2","pages":"Pages 131-171"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147865322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Synchronizing virtual backgrounds with monocular camera motion: A novel panoramic framework for video conferencing 同步虚拟背景与单目摄像机运动：一种新的视频会议全景框架

Virtual Reality Intelligent Hardware Pub Date : 2026-04-01 Epub Date: 2026-05-11 DOI: 10.1016/j.vrih.2026.01.003

Senzhe XU , Zian ZHOU , Fanglue ZHANG , Songhai ZHANG

引用次数: 0

From architecture to evaluation: A comprehensive review of video generation techniques 从架构到评估：视频生成技术的全面回顾

Virtual Reality Intelligent Hardware Pub Date : 2026-04-01 Epub Date: 2026-05-11 DOI: 10.1016/j.vrih.2026.03.002

Rong ZHANG , Chi WANG , Guojun LEI , Weiwei XU

{"title":"From architecture to evaluation: A comprehensive review of video generation techniques","authors":"Rong ZHANG , Chi WANG , Guojun LEI , Weiwei XU","doi":"10.1016/j.vrih.2026.03.002","DOIUrl":"10.1016/j.vrih.2026.03.002","url":null,"abstract":"<div><div>The rapid developments of artificial intelligence have significantly impacted daily life and content production modes. In the field of video generation, researchers are now exploring this emerging technique with innovative approaches, aiming to produce videos of higher quality, longer duration, and greater diversity. Currently, numerous video generation algorithms have been developed using different architecture designs. Unlike image generation, video generation requires maintaining consistency across both spatial and temporal dimensions while ensuring aesthetic quality and dynamic coherence, making it a more challenging task. In this survey, we provide a systematic review of existing video generation methods, tracing their evolution across different architectural paradigms. We further categorize recent models by their control conditions (e.g., text-to-video, image-to-video, multi-modal guidance) and summarize their unique theoretical foundations, architectural designs, and algorithmic innovations. In the meantime, we review the commonly used video datasets and analyze their applicability to different tasks. We also present evaluations of representative models to offer a more comprehensive perspective. Our goal is to provide a clear and concise overview of these algorithms, offering insights to support future breakthroughs in video generation.</div></div>","PeriodicalId":33538,"journal":{"name":"Virtual Reality Intelligent Hardware","volume":"8 2","pages":"Pages 172-201"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147865323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

CleanSplat: curriculum structural Gaussian splatting for spot-free novel view synthesis CleanSplat：课程结构高斯溅射，用于无点新颖视图合成

Virtual Reality Intelligent Hardware Pub Date : 2026-04-01 Epub Date: 2026-05-11 DOI: 10.1016/j.vrih.2026.02.001

Shengjia LIANG , Tong CHEN , Qichuan GENG , Yuan XIONG , Zhong ZHOU

{"title":"CleanSplat: curriculum structural Gaussian splatting for spot-free novel view synthesis","authors":"Shengjia LIANG , Tong CHEN , Qichuan GENG , Yuan XIONG , Zhong ZHOU","doi":"10.1016/j.vrih.2026.02.001","DOIUrl":"10.1016/j.vrih.2026.02.001","url":null,"abstract":"<div><div>3D Gaussian splatting (3DGS) has gained significant attention for its real-time, photorealistic rendering in novel view synthesis. However, its performance degrades severely when applied to real-world scenes with transients that break cross-view consistency. Existing methods typically attempt to identify and mask out these transients, but inherent masking errors often leave behind incoherent floating Gaussians, resulting in spotted artifacts that degrade the final scene quality. To address these limitations, we propose CleanSplat, a curriculum structural Gaussian splatting method that purifies the scene Gaussians through curriculum 3DGS optimization for transient removal and structural pruning of spotted artifacts. We introduce a curriculum-guided masking paradigm that generates coarse-to-fine transient masks from multi-scale features. The progressive optimization is driven by modulating the masking supervision based on current training state. To clear the spots, we propose a structure-aware handling strategy that employs a superpoint graph (SPG) partitioning of the Gaussians to perform principled identification and hierarchical pruning. This allows for the filtering of both intra-superpoint outliers and entire spurious superpoints based on local 3D coherence instead of only simple photometric consistency. By integrating curriculum 3DGS optimization and structural pruning, our method effectively separates the transients and purifies the static scene Gaussians. Extensive experiments on challenging datasets demonstrate that CleanSplat significantly outperforms state-of-the-art methods, delivering more detailed and cleaner novel view synthesis.</div></div>","PeriodicalId":33538,"journal":{"name":"Virtual Reality Intelligent Hardware","volume":"8 2","pages":"Pages 235-249"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147865368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DG-4DGS: deformation-graph-constrained 4D Gaussian splatting for temporally stable dynamic rendering DG-4DGS：变形图约束的4D高斯飞溅，用于暂时稳定的动态渲染

Virtual Reality Intelligent Hardware Pub Date : 2026-04-01 Epub Date: 2026-05-11 DOI: 10.1016/j.vrih.2026.04.001

Junyu CHEN , Mo SU , Dongdong WENG , Dong LI

{"title":"DG-4DGS: deformation-graph-constrained 4D Gaussian splatting for temporally stable dynamic rendering","authors":"Junyu CHEN , Mo SU , Dongdong WENG , Dong LI","doi":"10.1016/j.vrih.2026.04.001","DOIUrl":"10.1016/j.vrih.2026.04.001","url":null,"abstract":"<div><div>Accurately representing and rendering dynamic scenes over time remains a central challenge in neural rendering and computer graphics. Existing dynamic Gaussian-based methods often suffer from limited temporal consistency, flickering under fast motion, and poor adaptability to non-human structures. To address these issues, we propose DG-4DGS, a deformation-graph-constrained 4D Gaussian splatting framework for temporally stable dynamic rendering. The method anchors all Gaussians in a canonical space and enforces cross-frame geometric alignment through a deformation graph. Based on neighborhood-consistency features, a multi-head residual decoder refines position, rotation/scale, and color attributes to achieve fine-detail fidelity without relying on online densification or pruning. Compared with 4DGS and avatar-based approaches, DG-4DGS achieves higher PSNR (peak signal-to-noise ratio) and SSIM (structural similarity index measure) scores and significantly smaller model size on both the TalkBody4D (human) and Horse (non-human) datasets. It effectively suppresses temporal flickering and cross-frame drift in high-frequency regions such as hair strands, cloth wrinkles, and limb extremities. The framework does not depend on parametric templates, facilitating extension to non-human and complex clothing scenarios, though its performance still depends on deformation-tracking quality and neighborhood topology selection.</div></div>","PeriodicalId":33538,"journal":{"name":"Virtual Reality Intelligent Hardware","volume":"8 2","pages":"Pages 250-264"},"PeriodicalIF":0.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147865321","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing SS-OCT 3D image reconstruction: A real-time system with stripe artifact suppression and GPU parallel acceleration 增强SS-OCT三维图像重建：条带伪影抑制和GPU并行加速的实时系统

Virtual Reality Intelligent Hardware Pub Date : 2026-02-01 Epub Date: 2026-03-14 DOI: 10.1016/j.vrih.2025.12.003

Dandan LIU

{"title":"Enhancing SS-OCT 3D image reconstruction: A real-time system with stripe artifact suppression and GPU parallel acceleration","authors":"Dandan LIU","doi":"10.1016/j.vrih.2025.12.003","DOIUrl":"10.1016/j.vrih.2025.12.003","url":null,"abstract":"<div><div>Optical coherence tomography (OCT), particularly Swept-Source OCT, is widely employed in medical diagnostics and industrial inspections owing to its high-resolution imaging capabilities. However, Swept-Source OCT 3D imaging often suffers from stripe artifacts caused by unstable light sources, system noise, and environmental interference, posing challenges to real-time processing of large-scale datasets. To address this issue, this study introduces a real-time reconstruction system that integrates stripe-artifact suppression and parallel computing using a graphics processing unit. This approach employs a frequency-domain filtering algorithm with adaptive anti-suppression parameters, dynamically adjusted through an image quality evaluation function and optimized using a convolutional neural network for complex frequency-domain feature learning. Additionally, a graphics processing unit integrated 3D reconstruction framework is developed, enhancing data processing throughput and real-time performance via a dual-queue decoupling mechanism. Experimental results demonstrate significant improvements in structural similarity (0.92), peak signal-to-noise ratio (31.62 dB), and stripe suppression ratio (15.73 dB) compared with existing methods. On the RTX 4090 platform, the proposed system achieved an end-to-end delay of 94.36 milliseconds, a frame rate of 10.3 frames per second, and a throughput of 121.5 million voxels per second, effectively suppressing artifacts while preserving image details and enhancing real-time 3D reconstruction performance.</div></div>","PeriodicalId":33538,"journal":{"name":"Virtual Reality Intelligent Hardware","volume":"8 1","pages":"Pages 115-130"},"PeriodicalIF":0.0,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147454104","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Augmented reality surgical navigation: Clinical applications, key technologies, and future directions 增强现实手术导航：临床应用、关键技术及未来发展方向

Virtual Reality Intelligent Hardware Pub Date : 2026-02-01 Epub Date: 2026-03-14 DOI: 10.1016/j.vrih.2025.12.002

Yuanyuan WANG , Dawei LU , Jingfan FAN , Deqiang XIAO , Danni AI , Tianyu FU , Yucong LIN , Long SHAO , Tao CHEN , Hong SONG , Yongtian WANG , Jian YANG

{"title":"Augmented reality surgical navigation: Clinical applications, key technologies, and future directions","authors":"Yuanyuan WANG , Dawei LU , Jingfan FAN , Deqiang XIAO , Danni AI , Tianyu FU , Yucong LIN , Long SHAO , Tao CHEN , Hong SONG , Yongtian WANG , Jian YANG","doi":"10.1016/j.vrih.2025.12.002","DOIUrl":"10.1016/j.vrih.2025.12.002","url":null,"abstract":"<div><div>Surgical navigation has evolved significantly through advances in augmented reality, virtual reality, and mixed reality, improving precision and safety across many clinical applications, including neurosurgery, maxillofacial, spinal, and arthroplasty procedures. By integrating preoperative imaging with real-time intraoperative data, these systems provide dynamic guidance, reduce radiation exposure, and minimize tissue damage. Key challenges persist, including intraoperative registration accuracy, flexible tissue deformation, respiratory compensation, and real-time imaging quality. Emerging solutions include artificial intelligence-driven segmentation, deformation-field modeling, and hybrid registration techniques. Future developments will include lightweight, portable systems, improved non-rigid registration algorithms, and greater clinical adoption. Despite advances in rigid-tissue applications, soft-tissue navigation requires additional innovation to address motion variability and registration reliability, ultimately advancing minimally invasive surgery and precision medicine.</div></div>","PeriodicalId":33538,"journal":{"name":"Virtual Reality Intelligent Hardware","volume":"8 1","pages":"Pages 1-27"},"PeriodicalIF":0.0,"publicationDate":"2026-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147454101","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0