An Interior Space Layout Optimization Based on Wasserstein Generative Adversarial Networks with GraphSAGE

Since years, the interior space planning stage typically involves a labor intensive, iterative process that required manually balancing multiple factors, including meeting specific design and aesthetic goals by incorporating professional input, and optimizing design performance for efficiency and user experience. Traditional approaches for interior space layout optimization had face several challenges which include noise in labels, doesn't captured complex relationships. Therefore, this research proposes Wasserstein Generative Adversarial Networks (GANs)-GraphSAGE for interior space layout optimization. Initially, the data is taken from Regional Planning and Land Use Analysis Network (RPLAN) dataset. Then, data is preprocessed by using Soft label encoder which effectively captured uncertainty in labels. The preprocessed data is used for room graph generation by using Wasserstein GAN which effectively, generated more realistic room layouts by capturing complex relationships between objects. After that, layout generation is done by using GraphSAGE for capturing complex relationships between objects by enabling contextual layout generation. Finally, design and quality evaluation is done by using space syntax analysis which effectively, analyzed spatial relationships by revealing hidden patterns. The proposed Wasserstein GAN- GraphSAGE established better results, IOU of 0.19, precision 0.48, recall 0.50 when compared with existing Bicycle GAN.