Comparing GAN and Diffusion Models on an Interpretable 3D Voxel Dataset

• Aleksander Ogonowski

Room: https://cern.zoom.us/j/66151941204?pwd=n7upvvZYibexBhbtyn5kvTpy36L0Wo.1 Overview of generative models evaluated on a simple, visually interpretable 3D voxel dataset: * Creation of an easy-to-interpret 3D voxel dataset derived from 2D characters * Conditional WGAN-GP for fast 3D volume generation * Conditional diffusion model for smoother and more coherent volumetric synthesis * Evaluation using KID, PCC, and Separation Power metrics * Comparative analysis of generative behavior across increasing dataset complexity

Discussion Room: https://cern.zoom.us/j/66151941204?pwd=n7upvvZYibexBhbtyn5kvTpy36L0Wo.1