hzwer/ECCV2022-RIFE

ECCV2022 - Real-Time Intermediate Flow Estimation for Video Frame Interpolation

48
/ 100
Emerging

Implements optical flow-based frame interpolation using an intermediate flow estimation network that operates at 30+FPS for 2X 720p video on consumer GPUs, supporting arbitrary fractional timesteps between frame pairs. The architecture uses a multi-scale flow predictor with cost volume refinement, enabling efficient real-time inference without per-timestep retraining. Integrates with video processing pipelines via CLI tools, Docker, VapourSynth plugins, and ncnn-Vulkan backends for cross-platform deployment including mobile and game engine applications.

5,344 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

5,344

Forks

531

Language

Python

License

MIT

Last pushed

Sep 10, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/hzwer/ECCV2022-RIFE"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.