Session Full Program · Presenters · Organizations · Search Program · My Schedule · Happening NowMore…Search ProgramMy ScheduleHappening NowInvited Poster, Poster: Invited: PostersPresentationsFast But Accurate: A Real-Time Hyperelastic Simulator with Robust Frictional ContactContributorsZiqiu ZengSiyuan luoFan ShiText2VDM: Text to Vector Displacement Maps for Expressive and Interactive 3D SculptingContributorsHengyu MengDuotun WangZhijing ShaoLigang LiuZeyu WangDECON: Reconstruction of Clothed-Geometric Multiple Humans from a Single Image via Geometry-Guided DecouplingContributorsYiming JiangWenfeng SongShuai LiAimin HaoMagicScroll: Enhancing immersive storytelling with controllable scroll image generationContributorsBingyuan WangHengyu MengRui CaoZeyu CaiLanjiong LiYue MaQifeng ChenZeyu WangIterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference TuningContributorPengxiang LiHFHuman: High-Fidelity Human Reconstruction from Single Image with Multi-Modality FusionContributorsYiming JiangWenfeng SongShuai LiAimin HaoBernstein Bounds for CausticsContributorsZhimin FanChen WangYiming WangBoxuan LiYuxuan GuoLing-Qi YanYanwen GuoJie GuoOctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape GenerationContributorsSi-Tong WeiRui-Huan WangChuan-Zhi ZhouBaoquan ChenPeng-Shuai WangFast Determination and Computation of Self-intersections for NURBS SurfacesContributorsKai LiXiaohong JiaFalai ChenLove That Defies Mortality: Asymmetrical Transmedia Narrative and Interaction in the Chinese Classic Theatre The Peony PavilionContributorsZiyu KangZhaolong WangDingtian WangShan WangReal-Time Triangle-SDF Continuous Collision DetectionContributorsSheldon AndrewsAlexandre Mercier-AubinJoël Pelletier-GuénetteMMTL-UniAD: A Unified Framework for Multimodal and Multi-Task Learning in Assistive Driving PerceptionContributorsWenzhuo LiuWenshuo Wang"I don't like my avatar": Investigating Human Digital DoublesContributorsSiyi LiuKazi Injamamul HaqueZerrin YumakIMLS-Splatting: Efficient Mesh Reconstruction from Multi-view Images via Point RepresentationContributorsKaizhi YangDai LiuIsabella LiuXiaoshuai ZhangXiaoyan SunXuejin ChenZexiang XuHao SuFixTalk: Taming Identity Leakage for High-Quality Talking Head Generation in Extreme CasesContributorsShuai Tanye pan3D StreetUnveiler with Semantic-aware 2DGS - a simple baselineContributorsJingwei XuYikai WangYiqun ZhaoYanwei FuShenghua GaoImplicit Bézier Motion Model for Precise Spatial and Temporal ControlContributorsLuca VögeliDhruv AgrawalDominik BorerRobert SumnerMartin GuayJakob BuhmannVirtual and Traditional Memory Palaces in Recall with ADHDContributorsAnika JewstSusana CastilloMarcus MagnorMartin EisemannDagmar MeyerTopology-Aware Optimization of Gaussian Primitives for Human-Centric Volumetric VideosContributorChengcheng GuoSinGS: Animatable Single-Image Human Gaussian Splats with Kinematic PriorsContributorsYufan WuXuanhong ChenMonocular Mesh Recovery and Body Measurement of Female Saanen GoatsContributorBo JinBoolean Operation for CAD Models Using a Hybrid RepresentationContributorsYingyu YangXiaohong JiaBolun WangJieyin YangShiqing XinDong-Ming YanRepresenting Flow Fields with Divergence-Free Kernels for ReconstructionContributorsXingyu NiJingrui XingXingqiao LiBin WangBaoquan ChenDropoutGS: Dropping Out Gaussians for Better Sparse-view RenderingContributorsYexing XuLongguang WangMinglin ChenSheng AoLi LiYulan Guo3D Visual Illusion Depth EstimationContributorZhidan LiuBlind Inversion using Latent Diffusion PriorsContributorsWeimin BaiSiyi ChenWeijian LuoWenzheng ChenHe SunDeepMill: Neural Accessibility Learning for Subtractive ManufacturingContributorsFanchao ZhongYang WangPeng-Shuai WangLin LuHaisen ZhaoFlexiAct: Towards Flexible Action Control in Heterogeneous ScenariosContributorShiyi ZhangUnrealLLM: Towards Highly Controllable and Interactable 3D Scene Generation by LLM-powered Procedural Content GenerationContributorSong TangIntentMotion: Learning Intent-Aware Human Motion from Language in 3D SceneContributorsWenfeng SongShi ZhengXinyu ZhangXingliang JinAimin HaoFei HouXia HouShuai LiTransparentGS: Fast Inverse Rendering of Transparent Objects with GaussiansContributorsLetian HuangDongwei YeJialin DanChengzhi TaoHuiwen LiuKun ZhouBo RenYuanqi LiYanwen GuoJie GuoImperceptible Gaze Guidance Through Ocularity in Virtual RealityContributorsVirmarie MaquilingLi ZhaopingEnkelejda KasneciLongSplat: Online Generalizable 3D Gaussian Splatting from Long Sequence ImagesContributorGuichen HuangCityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale ScenesContributorJunran PengMesh2Brep: B-rep Reconstruction via Robust Primitive Fitting and Intersection-aware ConstraintsContributorsZeyu ShenMingyang ZhaoDong-Ming YanWencheng WangEvent TypeInvited Poster, PosterTimeWednesday, 17 December 20259:00am - 6:00pm HKTLocationChancellor 1+2, Level 4Registration CategoriesSimilar Sessions4D & Dynamic Scene Generation and ReconstructionAnimating Images, Sketches and TextGenerative Scenes & Panoramas
