Computer Vision Art Gallery

ICCV 2019, Seoul, Korea

Helena Sarin

Inferno, (2019)


This work is one of the #latentDoodles series. Though purely generative, the idea behind the series is to create marks evocative of human hand and folksy, but with hints of generative computational origin through pattern repetition and grid. Vis-à-vis abstract nature of generated images, i work carefully on image captioning, to give them additional (verbal) dimension

The image was generated by SNGAN trained on my sketches and doodles, upscaled with cycleGAN and then colorized by cycleGAN chaining to achieve the textural effect reminiscent of hell