ComboGAN: Unrestrained Scalability for Image Domain Translation Asha Anoosheh, Eirikur Augustsson, Radu Timofte, Luc van Gool In Arxiv, 2017.
https://arxiv.org/pdf/1712.06909.pdf
This year alone has seen unprecedented leaps in the area of learning-based image translation, namely CycleGAN, by Zhuet al. But experiments so far have been tailored to merely two domains at a time, and scaling them to more would re-quire an quadratic number of models to be trained. And with two-domain models taking days to train on current hardware,the number of domains quickly becomes limited by the time and resources required to process them. In this paper, we pro-pose a multi-component image translation model and training scheme which scales linearly - both in resource consumption and time required - with the number of domains. We demonstrate its capabilities on a dataset of paintings by 14different artists and on images of the four different seasons in the Alps. Note that 14 data groups would need(14choose2) =91 different CycleGAN models: a total of 182 genera-tor/discriminator pairs; whereas our model requires only 14generator/discriminator pairs
UNIT: UNsupervised Image-to-image Translation Networks : https://github.com/mingyuliutw/UNIT
Collaging like Painting with clouds...
Satellite Collections
digital prints
2009-2011
You can see from pole to pole and across oceans and continents and you can watch it turn and there's no strings holding it up, and it's moving in a blackness that is almost beyond conception.
-Eugene Cernan, an astronaut on the Apollo 17, on seeing the Earth from space
In all of these prints, I collect things that I've cut out from Google Satellite View-- parking lots, silos, landfills, waste ponds. The view from a satellite is not a human one, nor is it one we were ever really meant to see. But it is precisely from this inhuman point of view that we are able to read our own humanity, in all of its tiny, repetitive marks upon the face of the earth. From this view, the lines that make up basketball courts and the scattered blue rectangles of swimming pools become like hieroglyphs that say: people were here.
The alienation provided by the satellite perspective reveals the things we take for granted to be strange, even absurd. Banal structures and locations can appear fantastical and newly intricate. Directing curiosity toward our own inimitably human landscape, we may find that those things that are most recognizably human (a tangle of carefully engineered water slides, for example) are also the most bizarre, the most unlikely, the most fragile.
Site featuring the artwork of Jason Salavon. Work pages present a variety of projects created since 1991. The info pages include contact, CV, and publicity material. The feed contains posts, updates, and other newsy items.
Though photo manipulation has become more common in the age of digital cameras and image editing software, it actually dates back almost as far as the invention of photography. Gathered below is an overview of some of the more notable instances of photo manipulation in history. For recent years, an exhaustive inventory of every photo manipulation would be nearly impossible, so we focus here on the instances that have been most controversial or notorious, or ones that raise the most interesting ethical questions.