Generative dance images

How can we represent dance in an alternative form? 

The journey began with a happy accident. Last year I went to Kate Ware’s performance “Unstruck”.  “Unstruck” explores in movement and sound a process of live formation, like stones in a river, or sound through a tunnel. It is about energy and physical exchange. The piece was shown in conjunction with another exhibition Clifford Ross: “Water | Waves | Wood”.  I was fascinated by the performance and tried some exploration to remix the picture and movement. The result was just surprising.   

 

  1. Style transfer based on deep learning:

These works are implementations of “A Neural Algorithm of Artistic Style” by L. Gatys, A. Ecker, and M. Bethge in August 2015, a method for transferring the artistic style of one input image onto another using convolutional neural network. 

  • Unstruck by Kate Weare: (keyword: wave, energy)

unstruck0

Original content image from the screenshot of documentation video from Unstruck, and style images from the exhibition Clifford Ross: Water | Waves | Wood: 

4    

A more dynamic gif version:

unstruck_deeplearning

 

Other explorations:

  • Folding by Shenwei dance arts: (keyword: fold)

sample_4sample_1 sample_2 sample_3 sample_5

Original content image and style image:

  b

  • Folding by Shenwei dance arts: (keyword: fold)

folding_2_green folding_2_red

Original content image and style image:

  b

 

  • Folding by Shenwei dance arts: (keyword: fold)

62eb26fab26cdb6336220f060beec5b1

Original content image and style image:

  qaSpHGoWhuiIFyldxOrYXNLCR

 

2. Photo Mosaic based on keywords image search 

I integrated the mosaic algorithm here https://github.com/cinemast/OpenMosaic with google image custom search. The keywords are crawled from the different websites about each piece, currently I’m not able to tell the accuracy about these keywords.

  • Folding by Shenwei dance arts: (keywords: flesh, fold, shenwei, fabric, paper etc.)

folding_1 folding_3folding_0

Keyword: Cultural specificity, deviously beautiful, giggly young women, jagged path, drug addiction, intervention

Number of division: 21

Original :

  • Gif version of Tool is Loot, playing with different resolution and keywords:

 

Keywords: unnecessarily heavy eye, disingenuously anti-classical way, problematic new works, special guest stars

Number of devides: 47

47__The Bright Stream__0__ unnecessarily heavy eye__disingenuously anti-classical way__problematic new works__special guest stars

Original :

Keywords: male Season fairies,tense dramatic action,sublime ballerina type

Number of devides: 42

 

There are many more mosaics you can see here: http://restage.streamgao.com/wsearch/loadmore?loadmore=See+previous+examples.  They are made collectively by the users of my thesis restage.

My thesis is about meta data/meta media crawling for dance and generation of the photo mosaic. You are welcome to see this post and try the demo

 

One thought on “Generative dance images

  1. Pingback: restage - reexperience the internet dance – Stream Gao