Paper Notes
GitHub
SIGGRAPH Asia 2025 · Neural & Generative · 共 76 篇
  • SeqTex: Generate Mesh Textures in Video Sequence
  • ShapeGen: Towards High-Quality 3D Shape Synthesis
  • Shaping Strands with Neural Style Transfer
  • Spectral Prefiltering of Neural Fields
  • SPGen: Spherical Projection as Consistent and Flexible Representation for Single Image 3D Shape Generation
  • SS4D: Native 4D Generative Model via Structured Spacetime Latents
  • StyleSculptor: Zero-Shot Style-Controllable 3D Asset Generation with Texture-Geometry Dual Guidance
  • Teamwork: Collaborative Diffusion with Low-rank Coordination and Adaptation
  • The Aging Multiverse: Generating Condition-Aware Facial Aging Tree via Training-Free Diffusion
  • Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation
  • Unifying Latent Action and Latent State Pre-training for Policy Learning from Videos
  • UTDesign: A Unified Framework for Stylized Text Editing and Generation in Graphic Design Images
  • VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models
  • Virtually Being: Customizing Camera-Controllable Video Diffusion Models with Volumetric Performance Captures
  • Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off
  • Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation
  • WorldExplorer: Towards Generating Fully Navigable 3D Scenes
  • Zero-Shot Dynamic Concept Personalization with Grid-Based LoRA

    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

    Unifying Latent Action and Latent State Pre-training for Policy Learning from Videos

    Guangyan Chen, Meiling Wang, Te Cui, Luojie Yang, Qi Shao, Lin Zhao, Tianle Zhang, Yihang Li, Yi Yang, Yufeng Yue

    Beijing Institute of Technology

    SIGGRAPH Asia 2025Neural & Generative
    Robot LearningPolicy LearningLatent ActionVideo PretrainingImitation Learning
    Paper
    This note has no summary yet.