Slot-VAE: Object-Centric Scene Generation with Slot Attention
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910328082661376 |
|---|---|
| author | Wang, Yanbo Liu, Letao Dauwels, Justin |
| author_facet | Wang, Yanbo Liu, Letao Dauwels, Justin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_06997 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Slot-VAE: Object-Centric Scene Generation with Slot Attention Wang, Yanbo Liu, Letao Dauwels, Justin Computer Vision and Pattern Recognition 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. |
| title | Slot-VAE: Object-Centric Scene Generation with Slot Attention |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2306.06997 |