tinankh
Follow
Stars
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Refine high-quality datasets and visual AI models
JPEG Grid Detection based on the Number of DCT Zeros and its Application to Automatic and Localized Forgery Detection
A security tool to fingerprint PNG libraries used by web applications
JPEGsnoop: JPEG decoder and detailed analysis
Official implementation of "Diffusion models meet image counter-forensics"
Periodic plus smooth image decomposition, as described by Moisan (http://www.math-info.univ-paris5.fr/~moisan/papers/2009-11r.pdf)
On the detection of synthetic images generated by diffusion models
The HierText dataset contains ~12k images from the Open Images dataset v6 with large amount of text entities. We provide word, line and paragraph level annotations.
Models and examples built with TensorFlow
[ICCV 2023] Official implementation of the paper: "DIRE for Diffusion-Generated Image Detection"
A curated list of recent diffusion models for video generation, editing, restoration, understanding, etc.
ruptures: change point detection in Python
Image inpainting tool powered by SOTA AI Model. Remove any unwanted object, defect, people from your pictures or erase and replace(powered by stable diffusion) any thing on your pictures.
Official code for CAT-Net: Compression Artifact Tracing Network. Image manipulation detection and localization.
Automated Image Forgery Detection through Classification of JPEG Ghosts
Official Code for ICCV 2021 paper "Towards Flexible Blind JPEG Artifacts Removal (FBCNN)"
Detect dog face rect and facial landmarks(6 points) using dlib
[CVPR 2021 Oral] ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis
extract the dct coefficient of jpeg images. Provide c and python interface.
Source code of the article ''Noisesniffer: a Fully Automatic Image Forgery Detector Based on Noise Analysis" published in IWBF 2021.
A verification “Swiss army knife” helping journalists, fact-checkers, and human rights defenders to save time and be more efficient in their fact-checking and debunking tasks on social networks esp…