timmh/neural-supersampling
Unofficial re-implementation of a neural supersampling model for real-time rendering
This project helps game developers and 3D artists improve the visual quality of real-time rendered scenes without a significant performance hit. It takes lower-resolution images, along with depth and motion data, and intelligently upscales them to a higher resolution, making the graphics appear sharper and more detailed. The primary users are graphics programmers and technical artists working with 3D rendering pipelines.
No commits in the last 6 months.
Use this if you need to upscale real-time rendered graphics to a higher resolution while maintaining visual fidelity and performance, especially in games or interactive 3D applications.
Not ideal if you are looking for a general-purpose image upscaling tool for photographs or non-rendered media, or if you don't have access to depth and motion data.
Stars
31
Forks
7
Language
Python
License
MIT
Category
Last pushed
Jan 30, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/timmh/neural-supersampling"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
HasnainRaz/Fast-SRGAN
A Fast Deep Learning Model to Upsample Low Resolution Videos to High Resolution at 30fps
NatLabRockies/sup3r
The Super-Resolution for Renewable Resource Data (sup3r) software uses generative adversarial...
the-database/traiNNer-redux
Deep learning training framework for image super resolution and restoration.
eugenesiow/super-image
Image super resolution models for PyTorch.
movehand/raisr
A Python implementation of RAISR