Nikhil Rane

GAN based interior designs

In this project we have tried to automate the process of interior design. We view the process in the following ways : • The interior designer may want to generate a catalogue of random designs for the customer • The interior designer may want to guide the design process by provide sketches or custome styles • The interior designer may want to modify and existing design by adding, removing or modifying the objects We have tackled the three possibilites by the use of deep convolutional networks. We use GAN as the main algorithm to generate new designs. We also use GAN to modify an existing design. In addition we have also

used automatic segmentation to make the process of modification very user- friendly. We present the details of our implementation and the results we

We noticed that the closest popular dataset similar to Ikea room scenes is

the LSUN Bedroom dataset. We searched for various GANs that performed

Teaches professionals how to unlock the power of data to solve complex business problems and make data driven decisions. Designed by IISc, #1 ranked University (NIRF) and a premier academic institution for world-class education in science, engineering, and design. Delivered by TalentSprint with its deep understanding of the modern technologies, access to industry experts, and a state of art technology platform. Delivered in an executive-friendly format. Unique 5-step learning process of LIVE online faculty-led interactive sessions, capstone projects, mentorship, hackathons, and presentations to ensure fast-track learning.