taco-group/SparkVSR
SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation
This project helps video creators, digital archivists, or content producers enhance low-resolution video footage. It takes your existing low-quality video and a few selected "key" frames that you've already enhanced using an image upscaling tool. The output is a high-resolution, high-quality video where your keyframe improvements are propagated consistently throughout.
Use this if you have low-resolution videos that need significant quality improvement and you want precise control over the visual details of specific moments.
Not ideal if you need fully automatic video enhancement without any manual intervention or if you are working exclusively with still images.
Stars
29
Forks
—
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 18, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/taco-group/SparkVSR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
col14m/cadrille
[ICLR2026] cadrille: Multi-modal CAD Reconstruction with Online Reinforcement Learning
filaPro/cad-recode
[ICCV2025] CAD-Recode: Reverse Engineering CAD Code from Point Clouds
pengsongyou/openscene
[CVPR'23] OpenScene: 3D Scene Understanding with Open Vocabularies
worldbench/3EED
[NeurIPS 2025 DB Track] 3EED: Ground Everything Everywhere in 3D
cambrian-mllm/cambrian-s
Cambrian-S: Towards Spatial Supersensing in Video