Paper Notes
GitHub
SIGGRAPH 2026 · Image & Video · 共 24 篇
  • 2D Gaussian Splatting for Bézier Spline Line Art Vectorization
  • Adapting Quality Metrics to Tone Mapping
  • Autoregressive Modeling of Film with Applications in Video Montage
  • BFS: Back-to-Front Layered Image Synthesis via Knowledge Transfer
  • BoxCtrl: 3D-Aware Visual Prompting for Geometric Image Editing
  • DPF: Differentiable Polyphase Filtering for Large-Kernel Approximation
  • DreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learning
  • Generative Texture Filtering
  • HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos
  • Just-Dub-It: Video dubbing via Joint Audio-Visual Diffusion
  • LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models
  • LooseRoPE: Content-aware Attention Manipulation for Semantic Harmonization
  • LUCID: Learning Unified Control for Image Deflaring and Exposure Mastery in Nighttime Photography
  • Lucky High Dynamic Range Smartphone Imaging
  • MAOAM: Unified Object and Material Selection with Vision-Language Models
  • Pixel Cube: Diffusion-based Portrait Video Relighting Through Realistic Lighting Reproduction
  • Progressive Photorealistic Simplification
  • Relit-LiVE: Relight Video by Jointly Learning Environment Video
  • SmoothMotionVectors: Optimizing Your Content for Video Codecs in Free View Video Compression
  • Soft Anisotropic Diagrams for Differentiable Image Representation
  • StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition

    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

    DPF: Differentiable Polyphase Filtering for Large-Kernel Approximation

    Zhe Cao, Zhizhen Wu, Zhonggui Chen, Rui Wang, Yuchi Huo

    Zhejiang University; Xiamen University

    SIGGRAPH 2026Image & VideoImage FilteringLarge-Kernel ConvolutionPolyphase FilteringDifferentiable OptimizationGPU Acceleration
    Paper
    This note has no summary yet.