hzwer/ECCV2022-RIFE
ECCV2022 - Real-Time Intermediate Flow Estimation for Video Frame Interpolation
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.
Stars
5,344
Forks
531
Language
Python
License
MIT
Category
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.
Related models
ltkong218/IFRNet
IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation (CVPR 2022)
zzh-tech/InterpAny-Clearer
[TPAMI][ECCV2024 Oral] Clearer anytime frame interpolation & Manipulated interpolation of anything
danier97/ST-MFNet
[CVPR 2022] "ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation", Duolikun...
xuxy09/QVI
Implementation of "Quadratic video interpolation", NeurIPS 2019.
MegEngine/ECCV2022-RIFE
Official MegEngine Implementation of Real-Time Intermediate Flow Estimation for Video Frame Interpolation