chinese_ink_painting_style_transfer

https://github.com/chelsealiu0822/chinese_ink_painting_style_transfer

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
○
Academic publication links
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Unable to calculate vocabulary similarity

Last synced: 6 months ago · JSON representation ·

Repository

Basic Info

Host: GitHub
Owner: ChelseaLiu0822
Language: Jupyter Notebook
Default Branch: main
Size: 54.1 MB

Statistics

Stars: 0
Watchers: 1
Forks: 0
Open Issues: 0
Releases: 0

Created about 1 year ago · Last pushed about 1 year ago

Metadata Files

Readme Citation

README.md

ChineseInkPaintingStyleTransfer

Owner

Login: ChelseaLiu0822
Kind: user

Repositories: 1
Profile: https://github.com/ChelseaLiu0822

Citation (CITATION.cff)

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: >-
  Image-to-Chinese Ink Painting Style Transfer Using
  CycleGAN
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - given-names: 'Chelsea '
    family-names: Liu
    email: ql2547@nyu.edu
  - given-names: Yuewei
    family-names: Shi
    email: ys5795@nyu.edu
  - given-names: Yajie
    family-names: Zeng
    email: yz10383@nyu.edu
repository-code: >-
  https://github.com/ChelseaLiu0822/Chinese_Ink_Painting_Style_Transfer
abstract: >-
  This project focuses on advancing the application of
  Cycle-

  GAN to transform ordinary photographs into images inspired

  by the traditional Chinese ink painting style. Although
  the

  original CycleGAN has demonstrated significant potential
  in

  image-to-image translation tasks, it struggles to capture
  the

  nuanced artistic attributes of Chinese ink painting, such
  as

  expressive brush strokes, subtle ink wash diffusion, and
  dy-

  namic voids. To address these limitations, this work
  integrates

  enhanced loss functions, including brushstroke loss, ink
  wash

  loss, perceptual loss, and diffusion loss, inspired by
  recent ad-

  vancements in generative models. These additions ensure
  that

  the model preserves both the structural integrity of the
  input

  photographs and the artistic essence of Chinese ink
  paintings.

  Using a curated dataset of landscape photographs and ink

  paintings, the proposed model generates visually
  compelling

  results that emphasize authenticity and artistic style.
  This re-

  port outlines the dataset, methodology, loss functions,
  exper-

  imental setup, and preliminary results, with final
  refinements

  and evaluations to be conducted in subsequent iterations.
version: Release 0.0
date-released: '2024-12-17'

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science