A Generative Adversarial Network for AI-Aided Chair Design
This work addresses the challenge of automating design processes for furniture designers, but it appears incremental as it combines existing modules without major breakthroughs.
The paper tackles the problem of generating chair designs to aid human designers by using a generative adversarial network to create sketches and 3D models, resulting in the manual selection of one candidate to build a real chair for demonstration.
We present a method for improving human design of chairs. The goal of the method is generating enormous chair candidates in order to facilitate human designer by creating sketches and 3d models accordingly based on the generated chair design. It consists of an image synthesis module, which learns the underlying distribution of training dataset, a super-resolution module, which improve quality of generated image and human involvements. Finally, we manually pick one of the generated candidates to create a real life chair for illustration.