A Generative Adversarial Network for AI-Aided Chair Design

2019/03/01 by Zhibo Liu, Feng Gao, Yizhou Wang · 16 citations
Computer Science · Engineering · #Advanced Vision and Imaging #Adversarial system #Artificial intelligence #Computer Graphics and Visualization Techniques #Computer science #Engineering #Engineering drawing #Generative Adversarial Networks and Image Synthesis #Generative Design #Generative adversarial network #Generative grammar #Human–computer interaction #Image (mathematics) #Quality (philosophy) #cs.CV #cs.LG #eess.IV

paper · pdf · doi:10.1109/mipr.2019.00098

published in 2019 IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), 486-490 · 6 pages, 5 figures, accepted at MIPR2019

openalex publication_date 2019/03/01 · arxiv created 2020/01/31 · arxiv updated 2020/02/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

Abstract

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.

Citations

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Image-to-image translation for cross-domain disentanglement
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• A Style-Based Generator Architecture for Generative Adversarial Networks
• Deep learning
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Generative Adversarial Nets