2.5D stylized application using anisotropic reaction-diffusion

Abstract

Fig. 1: viz2viz generated samples (original data inset). From left to right: bird eye view of green forests with many trees, blue ocean with ships, grey city with many buildings, orange deserts; realistic stacks of red coca-cola coke cans, brown tea cups, glass wine bottles, starbucks paper coffee cups; realistic pink tulips; Ukiyo-e style side view of red wooden roller coaster, Ukiyo-e style blue sea waves and surfers. Note that in some examples in this paper, we select prompts to demonstrate the capabilities of viz2viz rather than for their aesthetic or design qualities.

Doom or Deliciousness: Challenges and Opportunities for Visualization in the Age of Generative Models

“…Often, in traditional visualization pipelines, a designer has to either be proficient in a programming language, or translate their ideas into tool‐specific operations [ SSL * 22 ], which makes for a steep learning curve. A number of tools seek to simplify the process, using either visual interfaces [ MC21 ], or, more recently, natural language [ SLJL10 , MS23 , DBSSD23 , WCA23 ] interfaces, which allow users to produce visualizations by simply typing or speaking their questions or requests. Recent surveys [ WCWQ22 , WWS * 22 , WH22 ] have explored how machine learning is being applied to the data visualization process.…”