anchen1011/toflow
TOFlow: Video Enhancement with Task-Oriented Flow
Unifies four video enhancement tasks—frame interpolation, denoising, deblocking, and super-resolution—using learned optical flow warping in a Torch/Lua architecture with spatial transformer networks (STN) for adaptive frame alignment. Includes the Vimeo-90K dataset (89,800 video clips across 448×256 sequences) and pre-trained models enabling direct inference on custom sequences via command-line demo scripts without retraining.
478 stars. No commits in the last 6 months.
Stars
478
Forks
93
Language
MATLAB
License
MIT
Category
Last pushed
Nov 11, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/anchen1011/toflow"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
NVlabs/nvdiffrec
Official code for the CVPR 2022 (oral) paper "Extracting Triangular 3D Models, Materials, and...
cvg/GlueStick
Joint Deep Matcher for Points and Lines 🖼️💥🖼️ (ICCV 2023)
RuojinCai/doppelgangers
Doppelgangers: Learning to Disambiguate Images of Similar Structures
microsoft/SpareNet
Style-based Point Generator with Adversarial Rendering for Point Cloud Completion (CVPR 2021)
fraunhoferhhi/neural-deferred-shading
Multi-View Mesh Reconstruction with Neural Deferred Shading (CVPR 2022)