Research map / Video / Video generation
Static-to-Dynamic: Animating Still Mattes via Generative Motion for Video Matting
Suqi Song, Jiaqi Xu, Jialuo He, Renjing Pei, Lei Chen, Lei Zhu
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes Static-to-Dynamic (S2D), which scales video matting training data by animating still labeled image-matte pairs into video-matte pairs using an image-to-video generative model.
Problem
Video matting is limited by the scarcity of diverse annotated video training data with alpha mattes.
Approach
Uses an image-to-video generation model to animate a static labeled image-matte pair, producing high-fidelity video-matte pairs so that abundant still matting annotations can be turned into dynamic training data.
Closest papers by meaning
- VideoMaMa: Mask-Guided Video Matting via Generative Prior (CVPR 2026 · similarity 0.93)
- $\alpha$Matte4K & $\mu$Matting: Dataset and Model for Ultra-Micro Precision Alpha Video Matting (CVPR 2026 · similarity 0.92)
- MatAnyone: Stable Video Matting with Consistent Memory Propagation (CVPR 2025 · similarity 0.89)
- MaGGIe: Masked Guided Gradual Human Instance Matting (CVPR 2024 · similarity 0.88)
- DRIP: Unleashing Diffusion Priors for Joint Foreground and Alpha Prediction in Image Matting (NeurIPS 2024 · similarity 0.87)
- Training Matting Models Without Alpha Labels (AAAI 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
