Paper Notes
GitHub
SIGGRAPH 2025 · Image & Video · 共 32 篇
  • FaceExpressions-70k: A Dataset of Perceived Expression Differences
  • Fast Isotropic Median Filtering
  • FlexiAct: Towards Flexible Action Control in Heterogeneous Scenarios
  • GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering
  • Generative Video Matting
  • Hybrid Tours: A Clip-based System for Authoring Long-take Touring Shots
  • Image-GS: Content-Adaptive Image Representation via 2D Gaussians
  • Instance Segmentation of Scene Sketches Using Natural Image Priors
  • InstantRestore: Single-Step Personalized Face Restoration with Shared-Image Attention
  • LayerFlow: A Unified Model for Layer-aware Video Generation
  • LightLab: Controlling Light Sources in Images with Diffusion Models
  • Mobius: Text to Seamless Looping Video Generation via Latent Shift
  • MonetGPT: Solving Puzzles Enhances MLLMs' Image Retouching Skills
  • Motion Inversion for Video Customization
  • Pocket Time-Lapse
  • Reenact Anything: Semantic Video Motion Transfer Using Motion-Textual Inversion
  • Sketch3DVE: Sketch-based 3D-Aware Scene Video Editing
  • VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control
  • VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control

    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

    LightLab: Controlling Light Sources in Images with Diffusion Models

    Nadav Magar, Amir Hertz, Eric Tabellion, Yael Pritch, Alex Rav-Acha, Ariel Shamir, Yedid Hoshen

    Tel Aviv University; Google; Reichman University; Hebrew University of Jerusalem

    SIGGRAPH 2025Image & Video
    RelightingDiffusion ModelImage EditingLight Source ControlParametric Control
    Paper
    This note has no summary yet.