Date of Award
Campus Access Thesis
Master of Science (MS)
Lap F. Yu
Creating 3D interiors is a challenging process. This is especially true with regards to creating a virtual room that matches a certain mood. There is no ensuring that the room will match the mood, since what each person considers a mood could be different. We propose a system for automatically changing the textures for objects within a 3D scene so that the scene matches a certain mood used as input. This is a valuable problem to tackle as it provides users with a tool for matching a mood to an environment with objective criteria. We use datasets of 10,000 images consisting of building/home interiors to train classifiers. This is done for five different moods. These classifiers are then used in an optimization process that scores the mood of a virtual scene. During each step of our optimization process textures of objects are modified until the classifier determines that the room matches the desired input mood. We believe that our approach can provide designers a valuable tool for creating 3D environments and can be used as a tool for studying perceptual design.
Solah, Michael, "Optimization of Virtual Indoor Environments According to Mood" (2018). Graduate Masters Theses. 544.
Available for download on Tuesday, December 31, 2019