YigitGunduc/vit-gan
paper: https://arxiv.org/abs/2110.09305
This project helps researchers and engineers transform images from one style to another, such as converting satellite maps to street views or daytime scenes to nighttime. It takes an input image and generates a corresponding output image that appears more realistic than those produced by other methods. This tool is ideal for anyone working with image manipulation tasks where generating highly realistic transformed images is crucial.
No commits in the last 6 months.
Use this if you need to translate images between different visual domains and prioritize the realism and quality of the generated output images.
Not ideal if your primary goal is simple image filtering or if you don't require highly realistic, style-transferred images.
Stars
18
Forks
7
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jan 30, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/YigitGunduc/vit-gan"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
mahmoudnafifi/C5
Reference code for the paper "Cross-Camera Convolutional Color Constancy" (ICCV 2021)
howardyclo/CLCC-CVPR21
An official TensorFlow implementation of “CLCC: Contrastive Learning for Color Constancy”...
heitorrapela/ModTr
[ECCV2024] ModTr: Modality Translation for Object Detection Adaptation Without Forgetting Prior Knowledge
lorenzobloise/transmission_tower_electrical_cable_instance_segmentation
This repository contains the code used to train and test a Mask R-CNN model for instance...