We introduce SlotDiffusion - an object-centric Latent Diffusion Model (LDM) designed for both image and video data. In this paper, we focus on improving slot-to-image decoding, a crucial aspect for high-quality visual generation. However, current slot-based methods often produce blurry images and distorted objects, exhibiting poor generative modeling capabilities. In addition, slot-based representations hold great potential for generative modeling, such as controllable image generation and object manipulation in image editing. Leveraging advanced architectures like Transformers, recent approaches have made significant progress in unsupervised object discovery. slots), providing structured representations that enable systematic generalization. Download a PDF of the paper titled SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models, by Ziyi Wu and 4 other authors Download PDF Abstract:Object-centric learning aims to represent visual data with a set of object entities (a.k.a.
