Graphics

Authors and titles for April 2025

[1] arXiv:2504.00234 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: CBIL: Collective Behavior Imitation Learning for Fish from Real Videos Show Chinese title

Title: 集体行为模仿学习（CBIL）：来自真实视频的鱼类研究

Yifan Wu, Zhiyang Dou, Yuko Ishiwaka, Shun Ogawa, Yuke Lou, Wenping Wang, Lingjie Liu, Taku Komura

Journal-ref: ACM Transactions on Graphics (TOG), 2024, Volume 43, Issue 6 Article No.: 242, Pages 1 - 17

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[2] arXiv:2504.00745 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: The Granule-In-Cell Method for Simulating Sand--Water Mixtures Show Chinese title

Title: 颗粒-细胞方法用于模拟砂-水混合物

Yizao Tang, Yuechen Zhu, Xingyu Ni, Baoquan Chen

Comments: 19 pages, 15 figures, To appear in ACM Transactions on Graphics (SIGGRAPH Asia 2025)

Subjects: Graphics (cs.GR) ; Fluid Dynamics (physics.flu-dyn)

[3] arXiv:2504.00904 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Explorable INR: An Implicit Neural Representation for Ensemble Simulation Enabling Efficient Spatial and Parameter Exploration Show Chinese title

Title: 可探索的隐式神经表示：一种启用高效空间和参数探索的集合模拟隐式神经表示

Yi-Tang Chen, Haoyu Li, Neng Shi, Xihaier Luo, Wei Xu, Han-Wei Shen

Comments: Accepted by IEEE Transactions on Visualization and Computer Graphics (TVCG)

Subjects: Graphics (cs.GR) ; Machine Learning (cs.LG)

[4] arXiv:2504.00983 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: WorldScore: A Unified Evaluation Benchmark for World Generation Show Chinese title

Title: WorldScore：一个用于世界生成的统一评估基准

Haoyi Duan, Hong-Xing Yu, Sirui Chen, Li Fei-Fei, Jiajun Wu

Comments: Project website: https://haoyi-duan.github.io/WorldScore/ The first two authors contributed equally

Subjects: Graphics (cs.GR) ; Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV)

[5] arXiv:2504.01016 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors Show Chinese title

Title: GeometryCrafter：带有扩散先验的一致性开放世界视频几何估计

Tian-Xing Xu, Xiangjun Gao, Wenbo Hu, Xiaoyu Li, Song-Hai Zhang, Ying Shan

Comments: Project webpage: https://geometrycrafter.github.io/

Subjects: Graphics (cs.GR) ; Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV)

[6] arXiv:2504.01027 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Mesh Compression with Quantized Neural Displacement Fields Show Chinese title

Title: 基于量化神经位移场的网格压缩

Sai Karthikey Pentapati, Gregoire Phillips, Alan C. Bovik

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[7] arXiv:2504.01204 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Articulated Kinematics Distillation from Video Diffusion Models Show Chinese title

Title: 从视频扩散模型中提炼articulated运动学

Xuan Li, Qianli Ma, Tsung-Yi Lin, Yongxin Chen, Chenfanfu Jiang, Ming-Yu Liu, Donglai Xiang

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[8] arXiv:2504.01338 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: FlowMotion: Target-Predictive Conditional Flow Matching for Jitter-Reduced Text-Driven Human Motion Generation Show Chinese title

Title: FlowMotion：用于抖动减少的文本驱动人体运动生成的目标预测条件流匹配

Manolo Canales Cuba, Vinícius do Carmo Melício, João Paulo Gois

Subjects: Graphics (cs.GR) ; Machine Learning (cs.LG)

[9] arXiv:2504.01358 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: 3D Gaussian Inverse Rendering with Approximated Global Illumination Show Chinese title

Title: 具有近似全局光照的3D高斯逆向渲染

Zirui Wu, Jianteng Chen, Laijian Li, Shaoteng Wu, Zhikai Zhu, Kang Xu, Martin R. Oswald, Jie Song

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[10] arXiv:2504.01402 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: A Survey on Physics-based Differentiable Rendering Show Chinese title

Title: 基于物理的可微分渲染综述

Yunfan Zeng, Guangyan Cai, Shuang Zhao

Comments: 12 pages, 8 figures

Subjects: Graphics (cs.GR)

[11] arXiv:2504.01483 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: GarmageNet: A Multimodal Generative Framework for Sewing Pattern Design and Generic Garment Modeling Show Chinese title

Title: GarmageNet：一种用于缝纫图案设计和通用服装建模的多模态生成框架

Siran Li, Chen Liu, Ruiyang Liu, Zhendong Wang, Gaofeng He, Yong-Lu Li, Xiaogang Jin, Huamin Wang

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[12] arXiv:2504.01571 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Pro-DG: Procedural Diffusion Guidance for Architectural Facade Generation Show Chinese title

Title: 面向建筑立面生成的程序扩散引导（Pro-DG）

Aleksander Plocharski, Jan Swidzinski, Przemyslaw Musialski

Comments: 12 pages, 13 figures

Subjects: Graphics (cs.GR) ; Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG)

[13] arXiv:2504.01786 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: BlenderGym: Benchmarking Foundational Model Systems for Graphics Editing Show Chinese title

Title: BlenderGym：用于图形编辑的基础模型系统基准测试

Yunqi Gu, Ian Huang, Jihyeon Je, Guandao Yang, Leonidas Guibas

Comments: CVPR 2025 Accepted

Subjects: Graphics (cs.GR) ; Machine Learning (cs.LG)

[14] arXiv:2504.01913 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Representing Flow Fields with Divergence-Free Kernels for Reconstruction Show Chinese title

Title: 用散度自由核表示流场以进行重建

Xingyu Ni, Jingrui Xing, Xingqiao Li, Bin Wang, Baoquan Chen

Subjects: Graphics (cs.GR) ; Machine Learning (cs.LG)

[15] arXiv:2504.01924 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Gen-C: Populating Virtual Worlds with Generative Crowds Show Chinese title

Title: Gen-C：用生成人群填充虚拟世界

Andreas Panayiotou, Panayiotis Charalambous, Ioannis Karamouzas

Comments: 11 pages

Subjects: Graphics (cs.GR) ; Machine Learning (cs.LG)

[16] arXiv:2504.02004 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Beyond Static Scenes: Camera-controllable Background Generation for Human Motion Show Chinese title

Title: 超越静态场景：可控摄像头的背景生成用于人体运动

Mingshuai Yao, Mengting Chen, Qinye Zhou, Yabo Zhang, Ming Liu, Xiaoming Li, Shaohui Liu, Chen Ju, Shuai Xiao, Qingwen Liu, Jinsong Lan, Wangmeng Zuo

Subjects: Graphics (cs.GR)

[17] arXiv:2504.02045 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Generating 360° Video is What You Need For a 3D Scene Show Chinese title

Title: 生成360°视频是您对3D场景所需的内容

Zhaoyang Zhang, Yannick Hold-Geoffroy, Miloš Hašan, Ziwen Chen, Fujun Luan, Julie Dorsey, Yiwei Hu

Comments: SIGGRAPH Asia 2025. Project Page: https://zhaoyangzh.github.io/projects/worldprompter/

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[18] arXiv:2504.02361 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: MG-Gen: Single Image to Motion Graphics Generation Show Chinese title

Title: MG-Gen：单张图像到动态图形生成

Takahiro Shirakawa, Tomoyuki Suzuki, Takuto Narumoto, Daichi Haraguchi

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[19] arXiv:2504.02465 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: RASP: Revisiting 3D Anamorphic Art for Shadow-Guided Packing of Irregular Objects Show Chinese title

Title: RASP：重新审视三维变形艺术以实现基于阴影引导的不规则物体包装

Soumyaratna Debnath, Ashish Tiwari, Kaustubh Sadekar, Shanmuganathan Raman

Comments: Conference on Computer Vision and Pattern Recognition (CVPR) 2025

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[20] arXiv:2504.02747 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: GEOPARD: Geometric Pretraining for Articulation Prediction in 3D Shapes Show Chinese title

Title: GEOPARD：用于三维形状运动预测的几何预训练

Pradyumn Goyal, Dmitry Petrov, Sheldon Andrews, Yizhak Ben-Shabat, Hsueh-Ti Derek Liu, Evangelos Kalogerakis

Subjects: Graphics (cs.GR)

[21] arXiv:2504.02875 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Real Time Animator: High-Quality Cartoon Style Transfer in 6 Animation Styles on Images and Videos Show Chinese title

Title: 实时动画师：图像和视频上六种动画风格的高质量卡通风格迁移

Liuxin Yang, Priyanka Ladha

Comments: 9 pages, images and videos with link

Subjects: Graphics (cs.GR)

[22] arXiv:2504.02879 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Robust AI-Synthesized Image Detection via Multi-feature Frequency-aware Learning Show Chinese title

Title: 基于多特征频率感知学习的鲁棒AI合成图像检测

Hongfei Cai, Chi Liu, Sheng Shen, Youyang Qu, Peng Gui

Subjects: Graphics (cs.GR)

[23] arXiv:2504.03099 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Learning Human Perspective in Line Drawings from Single Sketches Show Chinese title

Title: 从单一草图学习线条绘图中的人类视角

Jinfan Yang, Leo Foord-Kelcey, Suzuran Takikawa, Nicholas Vining, Niloy Mitra, Alla Sheffer

Subjects: Graphics (cs.GR)

[24] arXiv:2504.03415 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: NeRFlex: Resource-aware Real-time High-quality Rendering of Complex Scenes on Mobile Devices Show Chinese title

Title: NeRFlex：移动设备上资源感知的实时高质量复杂场景渲染

Zhe Wang, Yifei Zhu

Comments: This paper is accepted by 45th IEEE International Conference on Distributed Computing Systems (ICDCS 2025)

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG) ; Multimedia (cs.MM) ; Performance (cs.PF)

[25] arXiv:2504.03791 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Meshing of High-Dimensional Toroidal Manifolds from Quasi-Periodic Three-Body Problem Dynamics using Parameterization via Discrete One-Forms Show Chinese title

Title: 高维环面流形从准周期三体问题动力学的网格划分，使用离散一形式的参数化

Dante Basile, Xavier Tricoche, Martin Lo

Subjects: Graphics (cs.GR)

[26] arXiv:2504.03980 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Virtual Reality Lensing for Surface Approximation in Feature-driven DVR Show Chinese title

Title: 基于特征驱动的DVR表面逼近的虚拟现实透镜技术

Roberta Mota, Ehud Sharlin, Usman Alim

Subjects: Graphics (cs.GR)

[27] arXiv:2504.04000 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: View2CAD: Reconstructing View-Centric CAD Models from Single RGB-D Scans Show Chinese title

Title: View2CAD：从单个RGB-D扫描重建视点为中心的CAD模型

James Noeckel, Benjamin Jones, Adriana Schulz, Brian Curless

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[28] arXiv:2504.04153 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Video4DGen: Enhancing Video and 4D Generation through Mutual Optimization Show Chinese title

Title: Video4DGen：通过相互优化提升视频和4D生成

Yikai Wang, Guangce Liu, Xinzhou Wang, Zilong Chen, Jiafang Li, Xin Liang, Fuchun Sun, Jun Zhu

Comments: Published in TPAMI 2025. Code: https://github.com/yikaiw/Vidu4D, Project page: https://video4dgen.github.io

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[29] arXiv:2504.04298 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Samila: A Generative Art Generator Show Chinese title

Title: 萨米拉：一个生成艺术生成器

Sadra Sabouri, Sepand Haghighi, Elena Masrour

Comments: 13 pages, 7 figures

Subjects: Graphics (cs.GR) ; Human-Computer Interaction (cs.HC)

[30] arXiv:2504.04315 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Neural Parametric Mixtures for Path Guiding Show Chinese title

Title: 神经参数混合用于路径引导

Honghao Dong, Guoping Wang, Sheng Li

Comments: This paper has been published in ACM SIGGRAPH'23 proceedings. This version is a preprint one

Journal-ref: ACM SIGGGRAPH'2023

Subjects: Graphics (cs.GR)

[31] arXiv:2504.04411 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Hypothesis Testing for Progressive Kernel Estimation and VCM Framework Show Chinese title

Title: 渐进核估计和VCM框架的假设检验

Zehui Lin, Chenxiao Hu, Jinzhu Jia, Sheng Li

Comments: This paper has been published in IEEE Transactions on Visualization and Computer Graphics. This version is a preprint one

Journal-ref: IEEE Transactions on Visualization and Computer Graphics, 2023

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[32] arXiv:2504.04564 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: GPU Volume Rendering with Hierarchical Compression Using VDB Show Chinese title

Title: 使用VDB的分层压缩GPU体积渲染

Stefan Zellmann, Milan Jaros, Jefferson Amstutz, Ingo Wald

Subjects: Graphics (cs.GR) ; Distributed, Parallel, and Cluster Computing (cs.DC)

[33] arXiv:2504.04634 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: DanceMosaic: High-Fidelity Dance Generation with Multimodal Editability Show Chinese title

Title: DanceMosaic：具有多模态编辑能力的高保真舞蹈生成

Foram Niravbhai Shah, Parshwa Shah, Muhammad Usama Saleem, Ekkasit Pinyoanuntapong, Pu Wang, Hongfei Xue, Ahmed Helmy

Subjects: Graphics (cs.GR) ; Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG)

[34] arXiv:2504.04831 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: SMF: Template-free and Rig-free Animation Transfer using Kinetic Codes Show Chinese title

Title: 基于运动码的无模板无刚体约束动画迁移

Sanjeev Muralikrishnan, Niladri Shekhar Dutt, Niloy J. Mitra

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[35] arXiv:2504.04857 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: 3D Gaussian Particle Approximation of VDB Datasets: A Study for Scientific Visualization Show Chinese title

Title: VDB 数据集的三维高斯粒子近似：科学可视化的研究

Isha Sharma, Dieter Schmalstieg

Subjects: Graphics (cs.GR)

[36] arXiv:2504.04956 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: REWIND: Real-Time Egocentric Whole-Body Motion Diffusion with Exemplar-Based Identity Conditioning Show Chinese title

Title: 重放：基于实例的身份条件的自中心全身运动扩散的实时技术

Jihyun Lee, Weipeng Xu, Alexander Richard, Shih-En Wei, Shunsuke Saito, Shaojie Bai, Te-Li Wang, Minhyuk Sung, Tae-Kyun Kim, Jason Saragih

Comments: Accepted to CVPR 2025, project page: https://jyunlee.github.io/projects/rewind/

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[37] arXiv:2504.05296 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Let it Snow! Animating Static Gaussian Scenes With Dynamic Weather Effects Show Chinese title

Title: 下雪吧！ 带有动态天气效果的静态高斯场景动画

Gal Fiebelman, Hadar Averbuch-Elor, Sagie Benaim

Comments: Project webpage: https://galfiebelman.github.io/let-it-snow/

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[38] arXiv:2504.05482 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Imperative vs. Declarative Programming Paradigms for Open-Universe Scene Generation Show Chinese title

Title: 命令式与声明式编程范式在开放宇宙场景生成中的应用

Maxim Gumin, Do Heon Han, Seung Jean Yoo, Aditya Ganeshan, R. Kenny Jones, Rio Aguina-Kang, Stewart Morris, Daniel Ritchie

Subjects: Graphics (cs.GR) ; Programming Languages (cs.PL)

[39] arXiv:2504.05517 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: L3GS: Layered 3D Gaussian Splats for Efficient 3D Scene Delivery Show Chinese title

Title: L3GS：用于高效3D场景传输的分层三维高斯光点

Yi-Zhen Tsai, Xuechen Zhang, Zheng Li, Jiasi Chen

Subjects: Graphics (cs.GR) ; Machine Learning (cs.LG) ; Multimedia (cs.MM)

[40] arXiv:2504.05544 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: View-Dependent Deformation Fields for 2D Editing of 3D Models Show Chinese title

Title: 视点相关的变形场用于三维模型的二维编辑

Martin El Mqirmi, Noam Aigerman

Subjects: Graphics (cs.GR)

[41] arXiv:2504.05562 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Improved Stochastic Texture Filtering Through Sample Reuse Show Chinese title

Title: 通过样本重用来改进随机纹理过滤

Bartlomiej Wronski, Matt Pharr, Tomas Akenine-Möller

Comments: Accepted to 2025 ACM SIGGRAPH Symposium on Interactive 3D Graphics and Games (I3D 2025)

Journal-ref: Proceedings of the ACM on Computer Graphics and Interactive Techniques (2025), Volume 8, Issue 1, Article No: 14. Publication date: May 2025

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[42] arXiv:2504.05604 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: PyTopo3D: A Python Framework for 3D SIMP-based Topology Optimization Show Chinese title

Title: PyTopo3D：一种基于Python的3D SIMP拓扑优化框架

Jihoon Kim, Namwoo Kang

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[43] arXiv:2504.05740 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Micro-splatting: Multistage Isotropy-informed Covariance Regularization Optimization for High-Fidelity 3D Gaussian Splatting Show Chinese title

Title: 微点绘制：用于高保真3D高斯点绘制的多阶段各向同性信息协方差正则化优化

Jee Won Lee, Hansol Lim, Sooyeun Yang, Jongseong Brad Choi

Comments: This work has been submitted to journal for potential publication

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[44] arXiv:2504.05750 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Radiative Backpropagation with Non-Static Geometry Show Chinese title

Title: 辐射反向传播与非静态几何

Markus Worchel, Ugo Finnendahl, Marc Alexa

Comments: EGSR 2025

Journal-ref: Eurographics Symposium on Rendering (2025)

Subjects: Graphics (cs.GR)

[45] arXiv:2504.05803 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Revisiting Speech-Lip Alignment: A Phoneme-Aware Speech Encoder for Robust Talking Head Synthesis Show Chinese title

Title: 重新审视语音-嘴唇对齐：用于鲁棒说话头合成的音素感知语音编码器

Yihuan Huang, Jiajun Liu, Yanzhen Ren, Wuyang Liu, Zongkun Sun

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[46] arXiv:2504.06310 (cross-list from cs.GR) [cn-pdf, pdf, other]

Title: Conformal Slit Mapping Based Spiral Tool Trajectory Planning for Ball-end Milling on Complex Freeform Surfaces Show Chinese title

Title: 基于共形裂纹映射的螺旋刀具轨迹规划用于复杂自由曲面的球头铣削

Changqing Shen, BingZhou Xu, Xiaojian Zhang, Sijie Yan, Han Ding

Comments: The revised manuscript has improved the quality of the figures

Subjects: Graphics (cs.GR)

[47] arXiv:2504.06385 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Fast Globally Optimal and Geometrically Consistent 3D Shape Matching Show Chinese title

Title: 快速全局最优且几何一致的三维形状匹配

Paul Roetzer, Florian Bernard

Comments: 8 pages main paper, 9 pages supplementary

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[48] arXiv:2504.06598 (cross-list from cs.GR) [cn-pdf, pdf, other]

Title: Stochastic Ray Tracing of Transparent 3D Gaussians Show Chinese title

Title: 透明三维高斯随机光线追踪

Xin Sun, Iliyan Georgiev, Yun Fei, Miloš Hašan

Comments: 10 pages, 7 figures, 5 tables

Subjects: Graphics (cs.GR)

[49] arXiv:2504.07134 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Bringing Attention to CAD: Boundary Representation Learning via Transformer Show Chinese title

Title: 将注意力带到CAD：通过Transformer的边界表示学习

Qiang Zou, Lizhen Zhu

Journal-ref: Computer-Aided Design. 2025 Aug 26:103940

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[50] arXiv:2504.07210 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: MESA: Text-Driven Terrain Generation Using Latent Diffusion and Global Copernicus Data Show Chinese title

Title: MESA：基于潜在扩散和全球Copernicus数据的文本驱动地形生成

Paul Borne--Pons (Adobe Research, ESA), Mikolaj Czerkawski (Asterisk Labs, ESA), Rosalie Martin (Adobe Research), Romain Rouffet (Adobe Research)

Comments: Accepted at CVPR 2025 Workshop MORSE

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG)

[51] arXiv:2504.07485 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Rendering Large Volume Datasets in Unreal Engine 5: A Survey Show Chinese title

Title: 在虚幻引擎5中渲染大型体积数据集：综述

Markus Schlüter, Tom Kwasnitschka, Armin Bernstetter, Jens Karstens

Comments: Technical Report

Subjects: Graphics (cs.GR)

[52] arXiv:2504.07739 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Implicit Incompressible Porous Flow using SPH Show Chinese title

Title: 使用SPH的不可压缩多孔流

Timna Böttcher, Stefan Rhys Jeske, Lukas Westhofen, Jan Bender

Subjects: Graphics (cs.GR) ; Fluid Dynamics (physics.flu-dyn)

[53] arXiv:2504.07998 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: CDM-QTA: Quantized Training Acceleration for Efficient LoRA Fine-Tuning of Diffusion Model Show Chinese title

Title: CDM-QTA：用于扩散模型LoRA微调的量化训练加速

Jinming Lu, Minghao She, Wendong Mao, Zhongfeng Wang

Comments: ISCAS 2025

Subjects: Graphics (cs.GR) ; Artificial Intelligence (cs.AI) ; Hardware Architecture (cs.AR) ; Computer Vision and Pattern Recognition (cs.CV)

[54] arXiv:2504.07999 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: IGG: Image Generation Informed by Geodesic Dynamics in Deformation Spaces Show Chinese title

Title: IGG：基于变形空间中测地动力学的图像生成

Nian Wu, Nivetha Jayakumar, Jiarui Xing, Miaomiao Zhang

Subjects: Graphics (cs.GR)

[55] arXiv:2504.08022 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: ChildlikeSHAPES: Semantic Hierarchical Region Parsing for Animating Figure Drawings Show Chinese title

Title: 儿童般形状：用于动画人物绘画的语义分层区域解析

Astitva Srivastava, Harrison Jesse Smith, Thu Nguyen-Phuoc, Yuting Ye

Subjects: Graphics (cs.GR)

[56] arXiv:2504.08353 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Single View Garment Reconstruction Using Diffusion Mapping Via Pattern Coordinates Show Chinese title

Title: 基于扩散映射的单视角服装重建方法通过模式坐标

Ren Li, Cong Cao, Corentin Dumery, Yingxuan You, Hao Li, Pascal Fua

Comments: SIGGRAPH 2025

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG)

[57] arXiv:2504.08366 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: In-2-4D: Inbetweening from Two Single-View Images to 4D Generation Show Chinese title

Title: In-2-4D：从两个单视角图像到4D生成的补间

Sauradip Nag, Daniel Cohen-Or, Hao Zhang, Ali Mahdavi-Amiri

Comments: SIGGRAPH ASIA 2025; Project page at https://in-2-4d.github.io/

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[58] arXiv:2504.08383 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Generation of Zoomable maps with Rivers and Fjords Show Chinese title

Title: 可缩放地图中河流和峡湾的生成

Torben Æ. Mogensen, Emil N. Isenbecker

Subjects: Graphics (cs.GR)

[59] arXiv:2504.08541 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Dataset Show Chinese title

Title: 数字孪生目录：大规模照片级真实感3D对象数字孪生数据集

Zhao Dong, Ka Chen, Zhaoyang Lv, Hong-Xing Yu, Yunzhi Zhang, Cheng Zhang, Yufeng Zhu, Stephen Tian, Zhengqin Li, Geordie Moffatt, Sean Christofferson, James Fort, Xiaqing Pan, Mingfei Yan, Jiajun Wu, Carl Yuheng Ren, Richard Newcombe

Comments: accepted to CVPR 2025 (Highlight). Dataset page: https://www.projectaria.com/datasets/dtc/

Subjects: Graphics (cs.GR) ; Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO)

[60] arXiv:2504.08548 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: COP-GEN-Beta: Unified Generative Modelling of COPernicus Imagery Thumbnails Show Chinese title

Title: COP-GEN-Beta：COPernicus影像缩略图的统一生成建模

Miguel Espinosa, Valerio Marsocci, Yuru Jia, Elliot J. Crowley, Mikolaj Czerkawski

Comments: Accepted at CVPR 2025 Workshop MORSE

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[61] arXiv:2504.08937 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Rethinking Few-Shot Image Fusion: Granular Ball Priors Enable General-Purpose Deep Fusion Show Chinese title

Title: 重思Few-Shot图像融合：粒球先验实现通用深度融合

Minjie Deng, Yan Wei, Hao Zhai, An Wu, Yuncan Ouyang, Qianyao Peng

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG) ; Image and Video Processing (eess.IV) ; Machine Learning (stat.ML)

[62] arXiv:2504.09209 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation Show Chinese title

Title: EchoMask：基于语音查询的注意力掩码建模的全面协同言语运动生成

Xiangyue Zhang, Jianfang Li, Jiaxu Zhang, Jianqiang Ren, Liefeng Bo, Zhigang Tu

Comments: 12 pages, 12 figures

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV) ; Sound (cs.SD)

[63] arXiv:2504.09413 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Scalable Motion In-betweening via Diffusion and Physics-Based Character Adaptation Show Chinese title

Title: 基于扩散和物理的可扩展运动插值

Jia Qin

Subjects: Graphics (cs.GR)

[64] arXiv:2504.09553 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Procedural Multiscale Geometry Modeling using Implicit Functions Show Chinese title

Title: 基于隐函数的程序化多尺度几何建模

Bojja Venu, Adam Bosak, Juan Raul Padron-Griffe

Subjects: Graphics (cs.GR)

[65] arXiv:2504.09697 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: SPICE: A Synergistic, Precise, Iterative, and Customizable Image Editing Workflow Show Chinese title

Title: SPICE：一种协同、精确、迭代和可定制的图像编辑工作流程

Kenan Tang, Yanhong Li, Yao Qin

Comments: 24 pages, 21 figures. Figure 9(b) has been accepted by CVPR AI Art Gallery 2025

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG)

[66] arXiv:2504.09949 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Pseudo-Label Guided Real-World Image De-weathering: A Learning Framework with Imperfect Supervision Show Chinese title

Title: 伪标签引导的真实世界图像去雾：一种具有不完美监督的学习框架

Heming Xu, Xiaohui Liu, Zhilu Zhang, Hongzhi Zhang, Xiaohe Wu, Wangmeng Zuo

Comments: 15 pages, 16 figures

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[67] arXiv:2504.09975 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generation Show Chinese title

Title: OctGPT：基于八叉树的多尺度自回归模型用于3D形状生成

Si-Tong Wei, Rui-Huan Wang, Chuan-Zhi Zhou, Baoquan Chen, Peng-Shuai Wang

Comments: SIGGRAPH 2025

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[68] arXiv:2504.10620 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: SPreV Show Chinese title

Title: SPreV

Srivathsan Amruth

Comments: 45 Pages, 7 Figures, 3 Tables, 9 Algorithms, Opensource

Subjects: Graphics (cs.GR) ; Human-Computer Interaction (cs.HC) ; Machine Learning (cs.LG) ; Machine Learning (stat.ML)

[69] arXiv:2504.11003 (cross-list from cs.GR) [cn-pdf, pdf, other]

Title: 3D Gabor Splatting: Reconstruction of High-frequency Surface Texture using Gabor Noise Show Chinese title

Title: 3D Gabor 蒙版：使用 Gabor 噪声重建高频表面纹理

Haato Watanabe, Kenji Tojo, Nobuyuki Umetani

Comments: 4 pages, 5 figures, Eurographics 2025 Short Paper

Subjects: Graphics (cs.GR)

[70] arXiv:2504.11389 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: VideoPanda: Video Panoramic Diffusion with Multi-view Attention Show Chinese title

Title: VideoPanda：多视角注意力的视频全景扩散

Kevin Xie, Amirmojtaba Sabour, Jiahui Huang, Despoina Paschalidou, Greg Klar, Umar Iqbal, Sanja Fidler, Xiaohui Zeng

Comments: Project website at https://research.nvidia.com/labs/toronto-ai/VideoPanda/

Subjects: Graphics (cs.GR) ; Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV)

[71] arXiv:2504.11435 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Robust Containment Queries over Collections of Trimmed NURBS Surfaces via Generalized Winding Numbers Show Chinese title

Title: 通过广义环绕数对裁剪非均匀有理B样条曲面集合进行鲁棒的包含查询

Jacob Spainhour, Kenneth Weiss

Comments: 18 Pages, 16 Figures, 1 Table

Subjects: Graphics (cs.GR) ; Computational Geometry (cs.CG) ; Numerical Analysis (math.NA)

[72] arXiv:2504.11734 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Recent Advance in 3D Object and Scene Generation: A Survey Show Chinese title

Title: 三维物体和场景生成的最新进展：综述

Xiang Tang, Ruotong Li, Xiaopeng Fan

Comments: 34 pages, 6 figures

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[73] arXiv:2504.11936 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Mind2Matter: Creating 3D Models from EEG Signals Show Chinese title

Title: Mind2Matter: 使用EEG信号创建3D模型

Xia Deng, Shen Chen, Jiale Zhou, Lei Li

Subjects: Graphics (cs.GR) ; Human-Computer Interaction (cs.HC) ; Signal Processing (eess.SP)

[74] arXiv:2504.12237 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Stereoscopic Cylindrical Screen (SCS) Projection Show Chinese title

Title: 立体圆柱屏幕（SCS）投影

Lim Ngian Xin Terry, Adrian Xuan Wei Lim, Ezra Hill, Lynnette Hui Xian Ng

Subjects: Graphics (cs.GR)

[75] arXiv:2504.12351 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Prototype-Guided Diffusion for Digital Pathology: Achieving Foundation Model Performance with Minimal Clinical Data Show Chinese title

Title: 数字病理学的原型引导扩散：利用最少的临床数据实现基础模型性能

Ekaterina Redekop, Mara Pleasure, Vedrana Ivezic, Zichen Wang, Kimberly Flores, Anthony Sisk, William Speier, Corey Arnold

Subjects: Graphics (cs.GR) ; Artificial Intelligence (cs.AI) ; Image and Video Processing (eess.IV) ; Tissues and Organs (q-bio.TO)

[76] arXiv:2504.12451 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: One Model to Rig Them All: Diverse Skeleton Rigging with UniRig Show Chinese title

Title: 一个模型统管所有：使用UniRig进行多样骨骼绑定

Jia-Peng Zhang, Cheng-Feng Pu, Meng-Hao Guo, Yan-Pei Cao, Shi-Min Hu

Comments: 18 pages

Subjects: Graphics (cs.GR)

[77] arXiv:2504.12540 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: UniPhys: Unified Planner and Controller with Diffusion for Flexible Physics-Based Character Control Show Chinese title

Title: UniPhys：基于扩散的统一规划器和控制器用于灵活的物理角色控制

Yan Wu, Korrawe Karunratanakul, Zhengyi Luo, Siyu Tang

Comments: Project page: https://wuyan01.github.io/uniphys-project/

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO)

[78] arXiv:2504.12684 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: SOPHY: Learning to Generate Simulation-Ready Objects with Physical Materials Show Chinese title

Title: SOPHY：学习生成具有物理材料的仿真就绪对象

Junyi Cao, Evangelos Kalogerakis

Comments: Project page: https://xjay18.github.io/SOPHY_page

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[79] arXiv:2504.12776 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: StorySets: Ordering Curves and Dimensions for Visualizing Uncertain Sets and Multi-Dimensional Discrete Data Show Chinese title

Title: StorySets：按曲线和维度排序以可视化不确定集和多维离散数据

Markus Wallinger, Annika Bonerath, Wouter Meulemans, Martin Nöllenburg, Spehen Kobourov, Alexander Wolff

Subjects: Graphics (cs.GR)

[80] arXiv:2504.12788 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: ARAP-GS: Drag-driven As-Rigid-As-Possible 3D Gaussian Splatting Editing with Diffusion Prior Show Chinese title

Title: ARAP-GS：基于扩散先验的驱动拖拽式3D高斯随机点编辑的刚性保持变形

Xiao Han, Runze Tian, Yifei Tong, Fenggen Yu, Dingyao Liu, Yan Zhang

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[81] arXiv:2504.12800 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: CAGE-GS: High-fidelity Cage Based 3D Gaussian Splatting Deformation Show Chinese title

Title: CAGE-GS：基于高保真笼子的三维高斯点阵变形

Yifei Tong, Runze Tian, Xiao Han, Dingyao Liu, Fenggen Yu, Yan Zhang

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[82] arXiv:2504.12811 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: AAA-Gaussians: Anti-Aliased and Artifact-Free 3D Gaussian Rendering Show Chinese title

Title: AAA-Gaussians：抗锯齿且无伪影的3D高斯渲染

Michael Steiner, Thomas Köhler, Lukas Radl, Felix Windisch, Dieter Schmalstieg, Markus Steinberger

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[83] arXiv:2504.12856 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: 3D-PNAS: 3D Industrial Surface Anomaly Synthesis with Perlin Noise Show Chinese title

Title: 3D-PNAS: 使用Perlin噪声称的3D工业表面异常合成

Yifeng Cheng, Juan Du

Subjects: Graphics (cs.GR) ; Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG) ; Robotics (cs.RO)

[84] arXiv:2504.12909 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Real-time High-fidelity Gaussian Human Avatars with Position-based Interpolation of Spatially Distributed MLPs Show Chinese title

Title: 基于位置的时空分布MLP插值的实时高保真高斯人体虚拟人像

Youyi Zhan, Tianjia Shao, Yin Yang, Kun Zhou

Comments: CVPR 2025. Project page https://gapszju.github.io/mmlphuman/ . Code https://github.com/1231234zhan/mmlphuman

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[85] arXiv:2504.12999 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: GSAC: Leveraging Gaussian Splatting for Photorealistic Avatar Creation with Unity Integration Show Chinese title

Title: GSAC：利用高斯点云进行具有Unity集成的逼真虚拟形象创建

Rendong Zhang, Alexandra Watkins, Nilanjan Sarkar

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[86] arXiv:2504.13022 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: CompGS++: Compressed Gaussian Splatting for Static and Dynamic Scene Representation Show Chinese title

Title: CompGS++：静态和动态场景表示的压缩高斯泼溅

Xiangrui Liu, Xinju Wu, Shiqi Wang, Zhu Li, Sam Kwong

Comments: Submitted to a journal

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[87] arXiv:2504.13072 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: HiScene: Creating Hierarchical 3D Scenes with Isometric View Generation Show Chinese title

Title: HiScene：通过等距视图生成创建分层3D场景

Wenqi Dong, Bangbang Yang, Zesong Yang, Yuan Li, Tao Hu, Hujun Bao, Yuewen Ma, Zhaopeng Cui

Comments: Project webpage: https://zju3dv.github.io/hiscene/

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV) ; Multimedia (cs.MM)

[88] arXiv:2504.13204 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: EDGS: Eliminating Densification for Efficient Convergence of 3DGS Show Chinese title

Title: EDGS：消除3DGS的密度化以实现高效收敛

Dmytro Kotovenko, Olga Grebenkova, Björn Ommer

Subjects: Graphics (cs.GR)

[89] arXiv:2504.13206 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: DuoLoRA : Cycle-consistent and Rank-disentangled Content-Style Personalization Show Chinese title

Title: DuoLoRA：循环一致且排名解耦的内容-风格个性化

Aniket Roy, Shubhankar Borse, Shreya Kadambi, Debasmit Das, Shweta Mahajan, Risheek Garrepalli, Hyojin Park, Ankita Nayak, Rama Chellappa, Munawar Hayat, Fatih Porikli

Subjects: Graphics (cs.GR)

[90] arXiv:2504.13207 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: BEV-GS: Feed-forward Gaussian Splatting in Bird's-Eye-View for Road Reconstruction Show Chinese title

Title: 鸟瞰图中的前馈高斯点云投影：用于道路重建

Wenhua Wu, Tong Zhao, Chensheng Peng, Lei Yang, Yintao Wei, Zhe Liu, Hesheng Wang

Subjects: Graphics (cs.GR) ; Robotics (cs.RO)

[91] arXiv:2504.13226 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Image Editing with Diffusion Models: A Survey Show Chinese title

Title: 使用扩散模型的图像编辑：一项综述

Jia Wang, Jie Hu, Xiaoqi Ma, Hanghang Ma, Xiaoming Wei, Enhua Wu

Subjects: Graphics (cs.GR)

[92] arXiv:2504.13339 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Volume Encoding Gaussians: Transfer Function-Agnostic 3D Gaussians for Volume Rendering Show Chinese title

Title: 体积编码高斯：与传递函数无关的三维高斯用于体积渲染

Landon Dyken, Andres Sewell, Will Usher, Steve Petruzza, Sidharth Kumar

Subjects: Graphics (cs.GR)

[93] arXiv:2504.13378 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: SMPL-GPTexture: Dual-View 3D Human Texture Estimation using Text-to-Image Generation Models Show Chinese title

Title: SMPL-GPTexture：使用文生图生成模型的双视角三维人体纹理估计

Mingxiao Tu, Shuchang Ye, Hoijoon Jung, Jinman Kim

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[94] arXiv:2504.13386 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Supervising 3D Talking Head Avatars with Analysis-by-Audio-Synthesis Show Chinese title

Title: 通过音频合成进行分析的3D说话头像监督

Radek Daněček, Carolin Schmitt, Senya Polikovsky, Michael J. Black

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[95] arXiv:2504.13436 (cross-list from cs.GR) [cn-pdf, pdf, other]

Title: RT-HDIST: Ray-Tracing Core-based Hausdorff Distance Computation Show Chinese title

Title: RT-HDIST：基于光线追踪核心的豪斯多夫距离计算

YoungWoo Kim, Jaehong Lee, Duksu Kim

Comments: 8 pages, 7 figures

Subjects: Graphics (cs.GR) ; Computational Geometry (cs.CG)

[96] arXiv:2504.13448 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Ascribe New Dimensions to Scientific Data Visualization with VR Show Chinese title

Title: 赋予科学数据可视化新的维度与虚拟现实

Daniela Ushizima, Guilherme Melo dos Santos, Zineb Sordo, Ronald Pandolfi, Jeffrey Donatelli

Subjects: Graphics (cs.GR) ; Artificial Intelligence (cs.AI) ; Computational Engineering, Finance, and Science (cs.CE)

[97] arXiv:2504.14216 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: PyFRep: Shape Modeling with Differentiable Function Representation Show Chinese title

Title: PyFRep：基于可微函数表示的形状建模

Pierre-Alain Fayolle, Evgenii Maltsev

Comments: 21 pages, 10 figures. Code available at https://github.com/fayolle/PyFRep

Subjects: Graphics (cs.GR)

[98] arXiv:2504.14219 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: PRISM: A Unified Framework for Photorealistic Reconstruction and Intrinsic Scene Modeling Show Chinese title

Title: PRISM：逼真重建和内在场景建模的统一框架

Alara Dirik, Tuanfeng Wang, Duygu Ceylan, Stefanos Zafeiriou, Anna Frühstück

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[99] arXiv:2504.14257 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: HoLa: B-Rep Generation using a Holistic Latent Representation Show Chinese title

Title: HoLa：使用整体潜在表示的B-Rep生成

Yilin Liu, Duoteng Xu, Xingyao Yu, Xiang Xu, Daniel Cohen-Or, Hao Zhang, Hui Huang

Comments: ACM TOG and SIGGRAPH 2025 (Patent Protected); Project page: https://vcc.tech/research/2025/HolaBrep; Demo page: https://huggingface.co/spaces/YuXingyao/HoLa-BRep

Subjects: Graphics (cs.GR) ; Computer Vision and Pattern Recognition (cs.CV)

[100] arXiv:2504.14272 (cross-list from cs.GR) [cn-pdf, pdf, html, other]

Title: Can AI Recognize the Style of Art? Analyzing Aesthetics through the Lens of Style Transfer Show Chinese title

Title: AI能识别艺术风格吗？ 通过风格迁移分析美学

Yunha Yeo, Daeho Um

Comments: Accepted to ISEA 2025

Subjects: Graphics (cs.GR)