Research map / Video / Video generation
Oscillation Inversion: Training-Free Image and Video Enhancement Through Oscillated Latents in Large Flow Models
Yan Zheng, Zhenxiao Liang, Xiaoyan Cong, Yi Yang, Lanqing Guo, Yuehao Wang, Peihao Wang, Zhangyang Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| fuse Topaz outputs and degraded input with group inversion | Topaz per-frame enhancement · VFHQ video enhancement (Gaussian blur sigma=4) | T-LPIPS: 0.0215 -> 0.0179 | Improved |
| fuse Topaz outputs and degraded input with group inversion | Topaz per-frame enhancement · VFHQ video enhancement (Gaussian blur sigma=4) | CLIP TSC: 0.9910 -> 0.9922 | Improved |
| fuse Topaz outputs and degraded input with group inversion | Topaz per-frame enhancement · VFHQ video enhancement (Gaussian blur sigma=4) | flow L1: 5.0897 -> 5.1495 | Hurt |
| fuse Topaz outputs and degraded input with group inversion | Topaz per-frame enhancement · VFHQ video enhancement (Gaussian blur sigma=4) | flicker: 0.1317 -> 0.1376 | Hurt |
| apply oscillation inversion to SD3 instead of Flux or HunyuanVideo (ablation) | Oscillation Inversion · SD3 (qualitative) | oscillation phenomenon | Hurt |
| apply oscillation inversion to Flux-dev instead of Flux-schnell (ablation) | Oscillation Inversion · Flux-dev (qualitative) | oscillation phenomenon | No clear effect |
Closest papers by meaning
- Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations (ICLR 2025 · similarity 0.89)
- Taming Rectified Flow for Inversion and Editing (ICML 2025 · similarity 0.88)
- Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editing (CVPR 2025 · similarity 0.87)
- FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing (ICML 2025 · similarity 0.87)
- Text-to-Image Rectified Flow as Plug-and-Play Priors (ICLR 2025 · similarity 0.87)
- Lightning-Fast Image Inversion and Editing for Text-to-Image Diffusion Models (ICLR 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.
