Paper Notes
GitHub
SIGGRAPH 2025 · Animation & Simulation · 共 74 篇
  • Optimal r-Adaptive In-Timestep Remeshing for Elastodynamics
  • Painless Differentiable Rotation Dynamics
  • PARC: Physics-based Augmentation with Reinforcement Learning for Character Controllers
  • Physics-inspired Estimation of Optimal Cloth Mesh Resolution
  • PhysicsFC: Learning User-Controlled Skills for a Physics-Based Football Player Controller
  • PLT: Part-Wise Latent Tokens as Adaptable Motion Priors for Physically Simulated Characters
  • Progressive Dynamics++: A Framework for Stable, Continuous, and Consistent Animation Across Resolution and Time
  • Quadtree Tall Cells for Eulerian Liquid Simulation
  • Real-Time Knit Deformation and Rendering
  • RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets
  • Semantically Consistent Text-to-Motion with Unsupervised Styles
  • Shape Space Spectra
  • Sketch2Anim: Towards Transferring Sketch Storyboards into 3D Animation
  • SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrations
  • Solving partial differential equations in participating media
  • Stable Cosserat Rods
  • Stressful Tree Modeling: Breaking Branches with Strands
  • Tiny is not small enough: High quality, low-resource facial animation models through hybrid knowledge distillation
  • Variational Elastodynamic Simulation
  • ViSA: Physics-based Virtual Stunt Actors for Ballistic Stunts
  • xADA: Controllable and Expressive Audio-Driven Animation

    从搜索结果或列表筛选点进论文后，这里会显示那一批结果。

    Conference

    Semantically Consistent Text-to-Motion with Unsupervised Styles

    Linjun Wu, Xiangjun Tang, Jingyuan Cong, He Wang, Bo Hu, Xu Gong, Songnan Li, Yuchen Liao, Yiqian Wu, Chen Liu, Xiaogang Jin

    Zhejiang University; University of California San Diego; University College London; Tencent

    SIGGRAPH 2025Animation & Simulation
    Text-to-MotionMotion StylizationDiffusion ModelUnsupervised LearningSemantic Consistency
    PaperProject
    This note has no summary yet.