Object-centric learning aims to represent visual data with a set of object entities (a.k.a. slots), providing structured representations that enable systematic generalization. Leveraging advanced architectures like Transformers, recent approaches have made significant progress in unsupervised object discovery. In addition, slot-based representations hold great potential for generative modeling, such as controllable image generation and object manipulation in image editing. However, current slot-based methods often produce blurry images and distorted objects, exhibiting poor generative modeling capabilities. In this paper, we focus on improving slot-to-image decoding, a crucial aspect for high-quality visual generation. We introduce SlotDiffusion -- an object-centric Latent Diffusion Model (LDM) designed for both image and video data. Thanks to the powerful modeling capacity of LDMs, SlotDiffusion surpasses previous slot models in unsupervised object segmentation and visual generation across six datasets. Furthermore, our learned object features can be utilized by existing object-centric dynamics models, improving video prediction quality and downstream temporal reasoning tasks. Finally, we demonstrate the scalability of SlotDiffusion to unconstrained real-world datasets such as PASCAL VOC and COCO, when integrated with self-supervised pre-trained image encoders.

翻译：对象中心学习旨在通过一组对象实体（即slot）表示视觉数据，提供支持系统性泛化的结构化表示。借助Transformer等先进架构，近期方法在无监督对象发现方面取得了显著进展。此外，基于slot的表示在生成建模（如可控图像生成和图像编辑中的对象操控）中具有巨大潜力。然而，当前基于slot的方法常生成模糊图像和扭曲对象，生成建模能力较差。本文聚焦于优化slot到图像的解码——这一提升高质量视觉生成的关键环节。我们提出SlotDiffusion——一种面向图像和视频数据的对象中心潜扩散模型（LDM）。得益于LDM强大的建模能力，SlotDiffusion在六个数据集的非监督对象分割和视觉生成任务上超越了现有slot模型。此外，我们学习到的对象特征可被现有对象中心动态模型利用，从而提升视频预测质量及下游时序推理任务。最后，我们展示了SlotDiffusion在集成自监督预训练图像编码器后，可扩展至无约束真实世界数据集（如PASCAL VOC和COCO）。