Slot-VAE: Object-Centric Scene Generation with Slot Attention
This work addresses scene generation for computer vision applications, offering an incremental improvement over prior slot-based methods.
The paper tackles the problem of generating novel object-centric scenes by integrating slot attention with a hierarchical VAE framework, resulting in improved sample quality and scene structure accuracy compared to existing baselines.
Slot attention has shown remarkable object-centric representation learning performance in computer vision tasks without requiring any supervision. Despite its object-centric binding ability brought by compositional modelling, as a deterministic module, slot attention lacks the ability to generate novel scenes. In this paper, we propose the Slot-VAE, a generative model that integrates slot attention with the hierarchical VAE framework for object-centric structured scene generation. For each image, the model simultaneously infers a global scene representation to capture high-level scene structure and object-centric slot representations to embed individual object components. During generation, slot representations are generated from the global scene representation to ensure coherent scene structures. Our extensive evaluation of the scene generation ability indicates that Slot-VAE outperforms slot representation-based generative baselines in terms of sample quality and scene structure accuracy.