ZamDimon/distortion-generator
Neural network for creating distortion while keeping embeddings as close as possible
This tool generates visually distorted versions of original images, while ensuring that the core identity or features of the original image remain detectable by computer vision systems. It takes an image as input and outputs a distorted image. This is useful for researchers and developers working on privacy-preserving computer vision applications or robust image recognition systems.
No commits in the last 6 months.
Use this if you need to anonymize images for privacy reasons but still want them to be recognizable by AI, or to test the robustness of your image recognition models against visual alterations.
Not ideal if you need to create images that are completely unidentifiable by any system, or if you need to generate visually appealing artistic distortions.
Stars
20
Forks
2
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 06, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ZamDimon/distortion-generator"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huggingface/pytorch-pretrained-BigGAN
🦋A PyTorch implementation of BigGAN with pretrained weights and conversion scripts.
torchgan/torchgan
Research Framework for easy and efficient training of GANs based on Pytorch
metal3d/keras-video-generators
Keras generators to generate sequences from videos as input
GANs-in-Action/gans-in-action
Companion repository to GANs in Action: Deep learning with Generative Adversarial Networks
junyanz/pytorch-CycleGAN-and-pix2pix
Image-to-Image Translation in PyTorch