Generating Diverse Indoor Furniture Arrangements
This is an incremental improvement for interior design automation, enabling controlled diversity in furniture arrangements.
The paper tackles generating diverse indoor furniture arrangements by training a GAN on human-designed layouts and optimizing its latent space with a quality diversity algorithm, resulting in arrangements that match human designs while varying in price and furniture count.
We present a method for generating arrangements of indoor furniture from human-designed furniture layout data. Our method creates arrangements that target specified diversity, such as the total price of all furniture in the room and the number of pieces placed. To generate realistic furniture arrangement, we train a generative adversarial network (GAN) on human-designed layouts. To target specific diversity in the arrangements, we optimize the latent space of the GAN via a quality diversity algorithm to generate a diverse arrangement collection. Experiments show our approach discovers a set of arrangements that are similar to human-designed layouts but varies in price and number of furniture pieces.