一种轻量级旗帜飘扬视频生成方法及系统
By analyzing and segmenting a single static image to obtain optical flow vectors and motion candidate fields, and combining these with user control signals to generate continuous frame videos of a flag, the problem of stable deployment of image-to-video generation on resource-constrained devices is solved, achieving low-cost and controllable flag motion effects.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- UNIV OF SCI & TECH OF CHINA
- Filing Date
- 2026-04-29
- Publication Date
- 2026-07-17
AI Technical Summary
Existing image-to-video generation methods are difficult to deploy stably on resource-constrained terminals or payload-side devices, and the complex motion control results in high deployment costs, high system complexity, and difficulties in real-time interaction.
A lightweight approach is adopted to obtain optical flow vectors by parsing and segmenting target regions of a single static image, generating motion candidate fields, and constructing controlled motion fields by weighting user control signals, ultimately generating continuous frame videos of flags.
Under low computing resource conditions, it generates controllable and interpretable flag movement videos, suitable for popular science demonstrations and task simulation scenarios, providing intuitive explanations of physical phenomena and interactive visual feedback.
Smart Images
Figure CN122120577B_ABST