Buddhi19/SyntheticGen
[IGARSS 2026] Generates synthetic image–mask pairs by denoising joint latents conditioned on a real input image (VAE) and a class prompt (CLIP), enabling targeted oversampling of minority classes (e.g., barren) for LoveDA semantic segmentation.
Stars
11
Forks
2
Language
Python
License
MIT
Last pushed
Apr 06, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/synthetic-data/Buddhi19/SyntheticGen"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
benkeen/generatedata
A powerful, feature-rich, random test data generator.
sdv-dev/CTGAN
Conditional GAN for generating synthetic tabular data.
databrickslabs/dbldatagen
Generate relevant synthetic data quickly for your projects. The Databricks Labs synthetic data...
DexForce/EmbodiChain
An end-to-end, GPU-accelerated, and modular platform for building generalized Embodied Intelligence.
synthesized-io/tdk-demo
This is a collection of TDK demo projects that use different databases and options