Paper Notes
GitHub
SIGGRAPH Asia 2025 · Reconstruction · 共 40 篇
  • LLM-Primitives: Large Language Model for 3D Reconstruction with Primitives
  • LookUp3D: Data-Driven 3D Scanning
  • LVT: Large-Scale Scene Reconstruction via Local View Transformers
  • MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction
  • MODepth: Benchmarking Mobile Multi-frame Monocular Depth Estimation with Optical Image Stabilization
  • Neural Texture Splatting: Expressive 3D Gaussian Splatting for View Synthesis, Geometry, and Dynamic Reconstruction
  • PAD3R: Pose-Aware Dynamic 3D Reconstruction from Casual Videos
  • PhysHMR: Learning Humanoid Control Policies from Vision for Physically Plausible Human Motion Reconstruction
  • PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image
  • Prior-Enhanced Gaussian Splatting for Dynamic Scene Reconstruction from Casual Video
  • PriorAvatar: Efficient and Robust Avatar Creation from Monocular Video Using Learned Priors
  • RCTrans: Transparent Object Reconstruction in Natural Scene via Refractive Correspondence Estimation
  • Rigidity-Aware 3D Gaussian Deformation from a Single Image
  • Robust Single-shot Structured Light 3D Imaging via Neural Feature Decoding
  • Shoot-Bounce-3D: Single-Shot Occlusion-Aware 3D from Lidar by Decomposing Two-Bounce Light
  • Single-Image 3D Human Reconstruction with 3D-Aware Diffusion Priors and Facial Enhancement
  • Single-Shot Facial Capture using Polarized RGB Sinusoidal Illumination
  • Sketch2PoseNet: Efficient and Generalized Sketch to 3D Human Pose Prediction
  • SOF: Sorted Opacity Fields for Fast Unbounded Surface Reconstruction
  • Sparse SVBRDF Acquisition via Importance-Aware Illumination Multiplexing
  • Split4D: Decomposed 4D Scene Reconstruction Without Video Segmentation

    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

    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 2025Reconstruction
    Avatar ReconstructionMonocular Video3D Gaussian SplattingLearned PriorsHuman Avatar
    Paper
    This note has no summary yet.