IEEE transactions on visualization and computer graphics最新文献_第3页

AdaptiveShader: Adaptive Forward and Deferred Shading for Gaussian Splatting. AdaptiveShader：高斯喷绘的自适应前向和延迟着色。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-09-29 DOI: 10.1109/TVCG.2026.3738398

Zixuan Huang, Weihao Yu, Jin Huang

{"title":"AdaptiveShader: Adaptive Forward and Deferred Shading for Gaussian Splatting.","authors":"Zixuan Huang, Weihao Yu, Jin Huang","doi":"10.1109/TVCG.2026.3738398","DOIUrl":"https://doi.org/10.1109/TVCG.2026.3738398","url":null,"abstract":"Recent advances in 3D Gaussian Splatting have enabled real-time high-quality rendering, yet existing methods struggle to faithfully capture reflective surfaces. Prevailing methods often hardwire the shading strategy as either single-branch or rigid dual-branch, which limits their performance on reflective surfaces. In this work, we revisit the overlooked potential of forward shading and propose AdaptiveShader, a pixel-level adaptive shading framework that dynamically balances forward and deferred rendering. We first introduce an oracle model that selects per-pixel shading results by comparing both branches against ground-truth images. This oracle reveals the untapped benefits of forward shading and motivates our design. Since such ground-truth supervision is unavailable at test time, we further develop an affinity-based selection mechanism, which learns to assign pixel-wise weights to forward and deferred shading outputs. By adaptively leveraging the complementary strengths of both branches, our method outperforms existing methods in average novel-view synthesis performance on the two synthetic datasets and achieves the best average PSNR and SSIM on the Ref-Real dataset. Extensive experiments demonstrate that our method delivers strong average rendering fidelity, while the Ref-Real LPIPS results expose a remaining perceptual limitation.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149139896","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

Novel Encoding and Decoding Methods for Enhancing Short-Time High-Frequency VR-SSVEP Performance. 增强短波高频VR-SSVEP性能的新编解码方法。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-09-29 DOI: 10.1109/TVCG.2026.3738830

Dalu Zheng, Songyun Xie, Xinzhou Xi, Hao Tang, Bohan Li

{"title":"Novel Encoding and Decoding Methods for Enhancing Short-Time High-Frequency VR-SSVEP Performance.","authors":"Dalu Zheng, Songyun Xie, Xinzhou Xi, Hao Tang, Bohan Li","doi":"10.1109/TVCG.2026.3738830","DOIUrl":"10.1109/TVCG.2026.3738830","url":null,"abstract":"Virtual reality (VR) brain-computer interfaces (BCIs) based on steady-state visually evoked potentials (SSVEPs) face a critical challenge: achieving high information transfer rates (ITR) requires short time windows, while user comfort necessitates high-frequency stimulation. Decoding this high-frequency and short-time combination is highly challenging due to low signal-to-noise ratios. To address this, we applied the independent visual field stimulation (IVFS) paradigm to encode six high frequency targets (31-36 Hz) using three common encoding designs. Furthermore, we propose a novel Inter-class and Spatial Domain Collaborative Decoding (ICSD-CD) framework. By incorporating the Target-Band enhanced Spatial Decomposition Pattern (TB-eDSP) for lateralized feature extraction, ICSD CD synergistically integrates conventional inter-class difference (ICD) features with IVFS-specific spatial domain difference (SDD) features via a dynamic, confidence-based fusion strategy. Experimental results demonstrate that this framework effectively resolves the decoding bottleneck, achieving average accuracies of 89.11% (119.6 bits/min) with a 0.3 s data length and 93.93% (114 bits/min) with 0.5 s. This significantly outperforms single-domain methods, providing a viable pathway for high-performance VR BCIs.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149083259","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

HarmonPaint: Harmonized Training-Free Diffusion Inpainting. HarmonPaint：协调无训练扩散油漆。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-09-28 DOI: 10.1109/TVCG.2026.3735551

Xinzhe Li, Ying Li, Yong Du, Yangyang Xu, Junyu Dong, Shengfeng He

引用次数: 0

FrameTwin: Curve-Anchored Gaussian Alignment from Sparse Views for Adaptive Wireframe 3D Printing. FrameTwin：自适应线框3D打印的稀疏视图曲线锚定高斯对齐。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-09-23 DOI: 10.1109/TVCG.2026.3736685

Wenting Wang, Zhuo Huang, Kun Qian, Neelotpal Dutta, Yuhu Guo, Yingjun Tian, Yeung Yam, Charlie C L Wang

{"title":"FrameTwin: Curve-Anchored Gaussian Alignment from Sparse Views for Adaptive Wireframe 3D Printing.","authors":"Wenting Wang, Zhuo Huang, Kun Qian, Neelotpal Dutta, Yuhu Guo, Yingjun Tian, Yeung Yam, Charlie C L Wang","doi":"10.1109/TVCG.2026.3736685","DOIUrl":"10.1109/TVCG.2026.3736685","url":null,"abstract":"We present FrameTwin, a curve-anchored Gaussian alignment framework that uses sparse-view images to close the control loop for adaptive wireframe 3D printing. Our key idea is to capture the deformation of thin wireframe structures from sparse-view images using Gaussian kernels anchored to parametric curves, yielding a compact and geometry-aware encoding that explicitly captures strut topology. Driven by a differentiable rendering pipeline, FrameTwin estimates a neural deformation field that aligns the partially printed target model with the deformed structure observed during fabrication, where the optimized curve-Gaussian representation serves as a digital twin of the evolving wireframe. Unlike general Gaussian-splatting approaches, our formulation constrains kernel placement along parametric curves, substantially reducing the ambiguity inherent in sparse-view observations of thin structures. The resultant deformation-field alignment enforces global consistency across all struts. By using the estimated deformation field to blend the distorted printed geometry with the remaining unprinted geometry, FrameTwin enables adaptive updates to future printing trajectories. We demonstrate that FrameTwin can robustly capture and compensate for deformation in wireframe models fabricated using a robotized 3D printing system.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149032310","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

Label-aware Gaussian Splatting for Medical Volume Visualization in Mixed Reality. 混合现实中医学体可视化的标签感知高斯飞溅。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-09-23 DOI: 10.1109/TVCG.2026.3736595

Ruiyang Li, Chengkun Li, Yuqi Tong, Shi Qiu, Chi-Wing Fu, Pheng-Ann Heng

{"title":"Label-aware Gaussian Splatting for Medical Volume Visualization in Mixed Reality.","authors":"Ruiyang Li, Chengkun Li, Yuqi Tong, Shi Qiu, Chi-Wing Fu, Pheng-Ann Heng","doi":"10.1109/TVCG.2026.3736595","DOIUrl":"10.1109/TVCG.2026.3736595","url":null,"abstract":"Volume visualization is an important tool in exploring and understanding 3D medical data. Though the recent 3D Gaussian Splatting (3DGS) offers great potential for realtime high-quality medical volume visualization, directly applying 3DGS to visualize medical volume data often overlooks important anatomical structures, especially for vascular structures that are vital in disease detection and surgical planning. This paper presents a new framework called Label-aware Gaussian Splatting (LAGS) to leverage the inherent structural information of medical volumes and optimize the Gaussian representations, especially for fine-grained details of medical volume data. First, we introduce a new label attribute for Gaussian points and propose fine label initialization to enhance subsequent Gaussian training. Then, we devise a Label-aware Rasterizer (LAR) consisting of dual branches of differentiable rasterizers to jointly optimize photorealistic and structural representations. Next, we develop Label-aware Densification (LAD) to adaptively supplement Gaussians in regions with inferior structural representation. The above modules work synergistically during Gaussian training to encourage accurate reconstruction of delicate anatomical structures. We generate a dataset called MedVol-GS including medical scenes from various volumes and evaluate our method on it. Experiments show that LAGS outperforms existing NeRF and GS-based methods in rendering quality, with over 3 dB improvement in PSNR on average. Qualitative results reveal that our method has advantages in reconstructing intricate geometric structures even with occlusion and preventing floaters in nonlabeled areas. In addition, we enable real-time interaction at 72 FPS with labeled structures of reconstructed Gaussians in mixed reality (MR) for intuitive observation. A user study demonstrates that LAGS significantly improves medical volume visualization quality and experience for both clinicians and engineers in MR environments.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149032256","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

VIP-GS: Enhancing Sparse Novel View Synthesis via In-Place Virtual Viewpoint Inpainting. VIP-GS：基于原地虚拟视点的稀疏新视点合成。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-09-22 DOI: 10.1109/TVCG.2026.3736699

Haoyu Zhang, Shuaifeng Zhi, Zhenhua Du, Jingyuan Xia, Dewen Hu, Weidong Jiang

{"title":"VIP-GS: Enhancing Sparse Novel View Synthesis via In-Place Virtual Viewpoint Inpainting.","authors":"Haoyu Zhang, Shuaifeng Zhi, Zhenhua Du, Jingyuan Xia, Dewen Hu, Weidong Jiang","doi":"10.1109/TVCG.2026.3736699","DOIUrl":"https://doi.org/10.1109/TVCG.2026.3736699","url":null,"abstract":"While radiance field representations have achieved remarkable success in photo-realistic novel view synthesis with densely captured images, their performance sharply degrades under sparse input conditions, resulting in floater artifacts and missing regions caused by its inherent shape-radiance ambiguities and lack of informative observations, respectively. To address these challenges, we propose a few-shot 3DGS framework that leverages scene-adapted generative priors gated by multi-view geometric consistency to enhance the reconstruction quality for both interpolated and extrapolated views given limited observing viewpoints. Built upon coarse 3D Gaussians initiated via multi-view stereo, the core of our approach lies in lightweight personalized adaptation of a pretrained inpainting model from only the sparse input images, requiring no task-specific paired training data. During scene reconstruction, the current 3DGS reconstruction itself localizes unreliable virtual-view regions through multi-view warping consistency, where our personalized inpainting model is selectively invoked, and the repaired views are iteratively integrated to enrich the training corpus of Gaussian Splatting, progressively expanding the observing coverage and intensifying multi-view constraints. Extensive experimental results on three popular benchmark datasets including Tanks and Temples, MVImgNet and MipNeRF-360 demonstrate that our method, without using any specialized external training assets, dramatically improves the rendering quality of sparse-view novel view synthesis with a single consumer-grade GPU.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149042936","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

Neural Cone Radiosity for Interactive Global Illumination with Glossy Materials. 基于神经锥辐射的光滑材料交互全局照明。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-09-22 DOI: 10.1109/TVCG.2026.3736259

Jierui Ren, Haojie Jin, Bo Pang, Yisong Chen, Guoping Wang, Sheng Li

{"title":"Neural Cone Radiosity for Interactive Global Illumination with Glossy Materials.","authors":"Jierui Ren, Haojie Jin, Bo Pang, Yisong Chen, Guoping Wang, Sheng Li","doi":"10.1109/TVCG.2026.3736259","DOIUrl":"10.1109/TVCG.2026.3736259","url":null,"abstract":"Modeling of high-frequency outgoing radiance distributions has long been a key challenge in rendering, particularly for glossy materials. Such distributions concentrate radiative energy within a narrow lobe and are highly sensitive to changes in view direction. However, existing neural radiosity methods, which primarily rely on positional feature encoding, exhibit notable limitations in capturing these high-frequency, strongly view-dependent radiance distributions. To address this, we propose a highly-efficient approach by reflectance-aware ray cone encoding based on the neural radiosity framework, named neural cone radiosity. The core idea is to employ a pre-filtered multi-resolution hash grid to accurately approximate the glossy BSDF lobe, embedding view-dependent reflectance characteristics directly into the encoding process through continuous spatial aggregation. Our design not only significantly improves the network's ability to model high-frequency reflection distributions but also effectively handles surfaces with a wide range of glossiness levels, from highly glossy to low-gloss finishes. Meanwhile, our method reduces the network's burden in fitting complex radiance distributions, allowing the overall architecture to remain compact and efficient. Comprehensive experimental results demonstrate that our method consistently produces high-quality, visually clean renderings in real time under various glossiness conditions, and delivers superior fidelity and realism compared to baseline approaches.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149042959","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

Initialize to Generalize: A Stronger Initialization Pipeline for Sparse-View 3DGS. 初始化为一般化：一个更强的初始化管道为稀疏视图3DGS。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-09-22 DOI: 10.1109/TVCG.2026.3736471

Feng Zhou, Wenkai Guo, Pu Cao, Zhicheng Zhang, Jianqin Yin

{"title":"Initialize to Generalize: A Stronger Initialization Pipeline for Sparse-View 3DGS.","authors":"Feng Zhou, Wenkai Guo, Pu Cao, Zhicheng Zhang, Jianqin Yin","doi":"10.1109/TVCG.2026.3736471","DOIUrl":"10.1109/TVCG.2026.3736471","url":null,"abstract":"Sparse-view 3D Gaussian Splatting (3DGS) often overfits to the training views, leading to artifacts like blurring in novel view rendering. Prior work addresses it either by enhancing the initialization (i.e., the point cloud from Structure-from-Motion (SfM)) or by adding training-time constraints (regularization) to the 3DGS optimization. Yet our controlled ablations reveal that initialization is the decisive factor: it determines the attainable performance band in sparse-view 3DGS, while training-time constraints act as complementary refinements whose effectiveness depends on the initial geometric prior. Given initialization's primacy, we focus our design there. Although SfM performs poorly under sparse views due to its reliance on feature matching, it still provides reliable seed points. Thus, building on SfM, our effort aims to supplement the regions it fails to cover as comprehensively as possible. Specifically, we design: (i) frequency-aware SfM that improves low-texture coverage via low-frequency view augmentation and relaxed multi-view correspondences; (ii) 3DGS self-initialization that lifts photometric supervision into additional points, compensating SfM-sparse regions with learned Gaussian centers; and (iii) point-cloud regularization that enforces multi-view consistency and uniform spatial coverage through simple geometric/visibility priors, yielding a clean and reliable point cloud. Our experiments on LLFF and Mip-NeRF360 demonstrate consistent gains in sparse-view settings, establishing our approach as a stronger initialization strategy.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149027225","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

MeshSeqGen: Zero-shot Mesh Animation based on a Large Video Generation Model. MeshSeqGen：基于大型视频生成模型的零镜头网格动画。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-09-21 DOI: 10.1109/TVCG.2026.3735839

Yun-Peng Xiao, Jie Yang, Chuan Li, Lin Gao, Yong-Liang Yang

{"title":"MeshSeqGen: Zero-shot Mesh Animation based on a Large Video Generation Model.","authors":"Yun-Peng Xiao, Jie Yang, Chuan Li, Lin Gao, Yong-Liang Yang","doi":"10.1109/TVCG.2026.3735839","DOIUrl":"10.1109/TVCG.2026.3735839","url":null,"abstract":"Motion generation for 3D meshes is a fundamental task in computer animation, yet traditional methods like keyframe animation and motion capture are often costly and resource-intensive. Motivated by the progress in large-scale 2D video generation models, we introduce MeshSeqGen, a zero-shot framework that simplifies this process by using the motions from generated video frames to guide mesh deformation. Our method significantly differs from prior video-to-4D techniques lacking mesh-specific structural consistency, and other meshbased methods that require extensive 4D training data. To bridge the gap between 2D videos and 3D meshes, we design a mesh deformation network that learns from a pre-trained large video generation model and a multi-view synthesis model as spatialtemporal consistency guidance, while our mesh-based Gaussian representation ensures the final animations are both plausible and structurally consistent. Extensive evaluations demonstrate the performance of our method over existing approaches by producing diverse motions and high-quality mesh animations from simple text prompts, and making the process user-friendly and highly efficient without the need for complex rigging or keyframing.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149027228","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

Neural Motion Blur Rendering with Deformable Kernel Prediction. 神经运动模糊渲染与可变形核预测。

IF 6.5

IEEE transactions on visualization and computer graphics Pub Date : 2026-09-21 DOI: 10.1109/TVCG.2026.3735888

Cunhao Wu, Jiawei Huang, Shaokun Zheng, Fujun Luan, Kun Xu

{"title":"Neural Motion Blur Rendering with Deformable Kernel Prediction.","authors":"Cunhao Wu, Jiawei Huang, Shaokun Zheng, Fujun Luan, Kun Xu","doi":"10.1109/TVCG.2026.3735888","DOIUrl":"10.1109/TVCG.2026.3735888","url":null,"abstract":"We present a neural post-processing method for generating high-quality motion blur from sequences of statically rendered images and associated inexpensive by-products, such as feature buffers and motion vectors. Unlike traditional postprocessing approaches that apply fixed, local blur filters based on per-pixel motion, our method learns to synthesize motion blur in a content-aware, non-local manner. At the core of our approach is a U-Net-based convolutional neural network that extends the kernel-predicting network (KPN) paradigm: rather than predicting only blending weights for local neighborhoods, our network also predicts spatial offsets, allowing each pixel to gather information from a dynamically selected set of distant pixels along motion trajectories. This design enables the network to model complex motion blur patterns, including those caused by large displacements, occlusions, or nonlinear motion, with high visual fidelity. Our method operates entirely in image space, making it suitable for integration into offline production rendering pipelines without modifying the renderer itself. We demonstrate that our approach produces motion blur effects comparable to or exceeding those generated by physically accurate rendering, while requiring only a fraction of the computational cost. We evaluate our results across multiple representative scenes and show improved quality over equal-time path tracing and existing learning-based methods.","PeriodicalId":94035,"journal":{"name":"IEEE transactions on visualization and computer graphics","volume":"PP ","pages":""},"PeriodicalIF":6.5,"publicationDate":"2026-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149027182","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