Overview / Usage

“Shanshui–DaDA” is an interactive installation that utilizes a machine-learning algorithm in helping amateur participants realize traditional style Chinese Ink Wash Paintings. The audience is invited to sketch a simple line drawing representation of their ideal landscape painting in the software interface, through calculation, “Shanshui-DaDA” will generate a Chinese “Shanshui” based on the input drawn by the user. “Shanshui-DaDA” is the first of a series of explorations-“DaDA: Design and Draw with AI”- that seek to find AI’s role in traditionally human creativity centered areas. By way of challenging the creator’s conventional position, the artist poses the questions: Can we collaborate with AI to better facilitate, even enhance human creativity?

Methodology / Approach

"Shanshui-DaDA" is trained with "CycleGAN" (official PyTorch implementation) on 108 (later got expanded to 205 paintings) Shanshui paintings collected from online open data. The raw painting scans are pre-processed to 1772 pairs of edge-painting (sketches) and Shanshui paintings.

And the trained Pytorch model got ported to openVINO (More on how to port pytorch model to openVINO) and further wrapped with a nodejs based client-server system. User will sketch on the web interface and click to summit the sketch to backend node server and inference with openVINO.

A more detailed documentation including everything about how the project is developed from concept to implementation is here! (https://www.aven.cc/Shanshui-DaDA)

Repository

https://github.com/aaaven/ShanshuiDaDA_openVINO