image-quality-assessment
These-People-Do-Not-Exist
Our great sponsors
image-quality-assessment | These-People-Do-Not-Exist | |
---|---|---|
2 | 2 | |
2,000 | 15 | |
1.9% | - | |
0.0 | 0.0 | |
4 months ago | over 2 years ago | |
Python | Python | |
Apache License 2.0 | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
image-quality-assessment
-
And so it begins: AI(Midjourney) wins art competition without anyone realising.
It's an ongoing research area, but here's a Google model that assigns images ratings based on how good they look. It's pretty good, and it's from 2019 so not even close to state of the art. Paired with Stable Diffusion, it could indeed curate itself. I might have to try that actually.
- Extracting Images from Video
These-People-Do-Not-Exist
-
Github
two
-
TinyML: Deploying TensorFlow models to Android
A while back, researchers at NVIDIA released StyleGAN, a machine learning model that synthesizes images of pretty much anything from random noise, say images of landscapes, art, people, or vehicles. I saw a demo of it and it honestly blew my mind. Shortly after I implemented StyleGAN myself.
What are some alternatives?
student-teacher-anomaly-detection - Student–Teacher Anomaly Detection with Discriminative Latent Embeddings
Mask-RCNN-TF2 - Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow 2.0
GLOM-TensorFlow - An attempt at the implementation of GLOM, Geoffrey Hinton's paper for emergent part-whole hierarchies from data
IAmNotReal - App that uses machine learning to generate human faces
DarkMark - Marking up images for use with Darknet.
deepfake-scanner - Deepfake Scanner by Deepware.
imagededup - 😎 Finding duplicate images made easy!
ALAE - [CVPR2020] Adversarial Latent Autoencoders
image-super-resolution - 🔎 Super-scale your images and run experiments with Residual Dense and Adversarial Networks.
Crystal-Rush - An open world platformer game
efficientnet - Implementation of EfficientNet model. Keras and TensorFlow Keras.
robin - RObust document image BINarization