GaussianFluent: Gaussian Simulation for Dynamic Scenes with Mixed Materials
State Key Laboratory of General Artificial Intelligence, Peking University(北京大学通用人工智能国家重点实验室);State Key Laboratory of General Artificial Intelligence, BIGAI(北京大学通用人工智能国家重点实验室,BIGAI)
Bei Huang, Yixin Chen, Ruijie Lu, Gang Zeng, Hongbin Zha, Yuru Pei, Siyuan Huang
3D Gaussian Splatting (3DGS) has emerged as a prominent 3D representation for high-fidelity and real-time rendering. Prior work has coupled physics simulation with Gaussians, but predominantly targets soft, deformable materials, leaving brittle fracture largely unresolved. This stems from two key obstacles: the lack of volumetric interiors with coherent textures in GS representation, and the absence of fracture-aware simulation methods for Gaussians. To address these challenges, we introduce GaussianFluent, a unified framework for realistic simulation and rendering of dynamic object states. First, it synthesizes photorealistic interiors by densifying internal Gaussians guided by generative models. Second, it integrates an optimized Continuum Damage Material Point Method (CD-MPM) to enable brittle fracture simulation at remarkably high speed. Our approach handles complex scenarios including mixed-material objects and multi-stage fracture propagation, achieving results infeasible with previous methods. Experiments clearly demonstrate GaussianFluent's capability for photo-realistic, real-time rendering with structurally consistent interiors, highlighting its potential for downstream application, such as VR and Robotics.
Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splatting
School of Computer Science, Wuhan University(武汉大学计算机学院);School of Artificial Intelligence, Wuhan University(武汉大学人工智能学院);School of Electronic Information, Wuhan University(武汉大学电子信息学院);State Key Lab. of LIESMARS, Wuhan University(武汉大学LIESMARS国家重点实验室);Institute for Math & AI, Wuhan University(武汉大学数学与人工智能研究院)
RemixFusion: Residual-based Mixed Representation for Large-scale Online RGB-D Reconstruction
National Key Laboratory of Parallel and Distributed Computing(平行与分布式计算国家重点实验室);National University of Defense Technology(国防科技大学);Peking University(北京大学);Xiangjiang Laboratory(湘江实验室)
SparseGF: A Height-Aware Sparse Segmentation Framework with Context Compression for Robust Ground Filtering Across Urban to Natural Scenes
School of Remote Sensing and Geomatics Engineering, Nanjing University of Information Science and Technology(南京信息工程大学遥感与地理信息工程学院);Tiandu-Nuist Deep Space Exploration Laboratory(天都-南京信息工程大学深空探测实验室);School of Remote Sensing and Information Engineering, Wuhan University(武汉大学遥感与信息工程学院);School of Land Science and Technology, China University of Geosciences(中国地质大学(北京)土地科学与技术学院);School of Geospatial Artificial Intelligence, East China Normal University(华东师范大学地理信息智能学院);Department of Geography and Environmental Management, University of Waterloo(滑铁卢大学地理与环境管理系);Department of Systems Design Engineering, University of Waterloo(滑铁卢大学系统设计工程系)
FreeScene: Mixed Graph Diffusion for 3D Scene Synthesis from Free Prompts
School of Artificial Intelligence, Jilin University(吉林大学人工智能学院);School of Software, Shandong University(山东大学软件学院);Engineering Research Center of Knowledge-Driven Human-Machine Intelligence, MOE, China(知识驱动人机智能工程研究中心,教育部,中国)
Event-based Motion-Robust Accurate Shape Estimation for Mixed Reflectance Scenes
Department of Electrical Engineering, Rice University(电气工程系,里士大学);Wyant College of Optical Sciences, University of Arizona(光学科学学院,亚利桑那大学);Department of Electrical and Computer Engineering, Northwestern University(电气与计算机工程系,北western大学);Department of Computer Science, Northwestern University(计算机科学系,北western大学)
Mixed Neural Voxels for Fast Multi-view Video Synthesis
Beijing National Research Center for Information Science and Technology(北京国家信息科学与技术研究中心);Tsinghua University(清华大学);Hong Kong University of Science and Technology(香港科技大学);DAMO Academy, Alibaba Group(阿里巴巴集团达摩院)
LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes
Nanjing University of Aeronautics and Astronautics(南京航空航天大学);National University of Singapore(新加坡国立大学);Shanghai AI Laboratory(上海人工智能实验室);Nanjing University of Posts and Telecommunications(南京邮电大学);S-Lab, Nanyang Technological University(南洋理工大学S-Lab)
Mixed Text Recognition with Efficient Parameter Fine-Tuning and Transformer
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences, China(深圳先进技术研究院,中国科学院,中国);The Institute of Technological Sciences, Wuhan University, China(技术科学学院,武汉大学,中国)
OccludeNet: A Causal Journey into Mixed-View Actor-Centric Video Action Recognition under Occlusions
Sanya Science and Education Innovation Park, Wuhan University of Technology, Sanya 572025, China(武汉理工大学三亚科技创新园);Hubei Key Laboratory of Transportation Internet of Things, Wuhan University of Technology, Wuhan 430070, China(武汉理工大学交通物联网重点实验室);State Key Laboratory for Multimedia Info Processing, Peking University, Beijing 100871, China(北京大学信息处理国家重点实验室);Hubei Key Laboratory of Big Data Intelligent Analysis, Hubei University, Wuhan 430062, China(湖北大学大数据智能分析重点实验室);National Engineering Research Center for Multimedia Software, Wuhan University, Wuhan 430072, China(武汉大学多媒体软件工程研究中心);Department of Electrical Engineering, National Tsing Hua University, Hsinchu 30013, Taiwan(清华大学电子工程系)
针对视频动作识别中遮挡数据不足的问题,本文构建涵盖真实与合成场景的大规模 OccludeNet 数据集,并提出基于结构因果模型、后门调整和反事实推理的 CAR 方法以增强遮挡鲁棒性。
Task-Oriented Communications for 3D Scene Representation: Balancing Timeliness and Fidelity
School of Computing Science, University of Glasgow(格拉斯哥大学计算科学学院);Department of Computer Science, University of Manchester(曼彻斯特大学计算机科学系);School of Engineering, University of Glasgow(格拉斯哥大学工程学院)
Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction
Archimedes Athena Research Center(雅典娜研究中心);National Technical University of Athens(雅典国家技术大学);University of Crete(克里特大学);IACM-Forth(希腊研究与技术基金会-应用与计算数学研究所)