Paper Notes
GitHub

附近论文

SIGGRAPH Asia 2025 · 全部 301 篇
  • PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image
  • ADD: Physics-Based Motion Imitation with Adversarial Differential Discriminators
  • PhysiOpt: Physics-Driven Shape Optimization for 3D Generative Models
  • PoissonNet: A Local-Global Approach for Learning on Surfaces
  • Potentially Visible Set Generation with the Disocclusion Buffer
  • PowerGS: Display-Rendering Power Co-Optimization for Neural Rendering in Power-Constrained XR Systems
  • Practical Gaussian Process Implicit Surfaces with Sparse Convolutions
  • PractiLight: Practical Light Control Using Foundational Diffusion Models
  • Precise Gradient Discontinuities in Neural Fields for Subspace Physics
  • Prior-Enhanced Gaussian Splatting for Dynamic Scene Reconstruction from Casual Video
  • PriorAvatar: Efficient and Robust Avatar Creation from Monocular Video Using Learned Priors
  • Procedural Scene Programs for Open-Universe Scene Generation: LLM-Free Error Correction via Program Search
  • Progressive Outfit Assembly and Instantaneous Pose Transfer
  • Proteus-ID: ID-Consistent and Motion-Coherent Video Customization
  • QMF-Blend: Quantized Matrix Factorization for Efficient Blendshape Compression
  • RaRa Clipper: A Clipper for Gaussian Splatting Based on Ray Tracer and Rasterizer
  • RCTrans: Transparent Object Reconstruction in Natural Scene via Refractive Correspondence Estimation
  • Realistic Cloth Rendering with a Ray-Wave Hybrid Shading Model
  • Reconfigurable Hinged Kirigami Tessellations
  • ReSTIR PG: Path Guiding with Spatiotemporally Resampled Paths
  • RibbonSculpt: Voronoi Ball based 3D Sculpting from Sparse VR Ribbons
Conference

PriorAvatar: Efficient and Robust Avatar Creation from Monocular Video Using Learned Priors

Tianjian Jiang, Hsuan-I Ho, Manuel Kaufmann, Jie Song

ETH Zurich

SIGGRAPH Asia 2025ReconstructionAvatar ReconstructionMonocular Video3D Gaussian SplattingLearned PriorsHuman Avatar
Paper
This note has no summary yet.