liyuantsao/BFSR
The official repository of BFSR: "Boosting Flow-based Generative Super-Resolution Models via Learned Prior" [CVPR 2024]
This project helps improve the quality and realism of images that have been enlarged or upscaled, especially when you need to generate new details rather than just stretching existing pixels. It takes a low-resolution image and outputs a much sharper, more detailed, and visually consistent high-resolution image, even for unusual or very large scaling factors. This would be used by professionals in fields like digital media, forensics, or scientific imaging who need to enhance visual data for analysis or display.
No commits in the last 6 months.
Use this if you need to significantly improve the detail and visual fidelity of low-resolution images, especially when artifacts like grid patterns or unnatural-looking expansions are a problem with current upscaling methods.
Not ideal if your primary goal is simple, fast image resizing without needing advanced generative detail or artifact correction, or if you only work with images that are already high quality.
Stars
85
Forks
5
Language
Python
License
—
Category
Last pushed
Jun 13, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/liyuantsao/BFSR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AngeClementAkazan/Sequential-FeatureForestFlow
This repository contains the code source of the Heterogeneous Sequential Feature Forest Flow...
AlejandroMllo/action_flow_matching
Code for the paper "Action Flow Matching for Continual Robot Learning" presented at Robotics:...
dsgiitr/flux-watermarking
Official Implementation of the paper WMARK@ICLR Detection Limits and Statistical Separability of...
ericbill21/FOCUS
Official codebase for FOCUS: Optimal Control Meets Flow Matching: A Principled Route to...
lebellig/flow-matching
Annotated Flow Matching paper