alexjc/neural-doodle
Turn your two-bit doodles into fine artworks with deep neural networks, generate seamless textures from photos, transfer style from one image to another, perform example-based upscaling, but wait... there's more! (An implementation of Semantic Style Transfer.)
ArchivedBased on the README, here's a technical summary: Implements semantic style transfer via iterative patch matching—the algorithm extracts annotated regions from a style reference and incrementally synthesizes them onto a target using deep neural network features, supporting multi-phase refinement with configurable layer matching and smoothness constraints. Built for CPU and CUDA GPU rendering with Docker containerization; accepts optional semantic segmentation masks (*_sem.png) to guide style transfer while preserving structural correspondences between images.
9,879 stars. No commits in the last 6 months.
Stars
9,879
Forks
898
Language
Python
License
AGPL-3.0
Category
Last pushed
Oct 01, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/alexjc/neural-doodle"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
rgeirhos/Stylized-ImageNet
Code to create Stylized-ImageNet, a stylized version of standard ImageNet (ICLR 2019 Oral)
cysmith/neural-style-tf
TensorFlow (Python API) implementation of Neural Style
ProGamerGov/neural-style-pt
PyTorch implementation of neural style transfer algorithm
reiinakano/arbitrary-image-stylization-tfjs
Arbitrary style transfer using TensorFlow.js
gordicaleksa/pytorch-neural-style-transfer
Reconstruction of the original paper on neural style transfer (Gatys et al.). I've additionally...