mlsanityData to 7 Oct 2026

Slot-VAE: Object-Centric Scene Generation with Slot Attention

arXiv 2306.06997 ↗First posted 12 Jun 2023cs.CVcited by 20

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 35 of its 52 references that are in the map. First posted on arXiv 12 Jun 2023.

Builds on

35 of 52 references.

References · 35

  1. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  2. 2013Auto-Encoding Variational Bayescited by 3,980
  3. 2018World Modelscited by 1,444
  4. 2020Object-Centric Learning with Slot Attentioncited by 865
  5. 2020GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fieldscited by 784
  6. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 388
  7. 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 359
  8. 2017A simple neural network module for relational reasoningcited by 345
  9. 2021Conditional Object-Centric Learning from Videocited by 247
  10. 2020On the Binding Problem in Artificial Neural Networkscited by 230
  11. 2019GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representationscited by 227
  12. 2022Bridging the Gap to Real-World Object-Centric Learningcited by 219
23 more
  1. 2016Attend, Infer, Repeat: Fast Scene Understanding with Generative Modelscited by 209
  2. 2019Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishingcited by 191
  3. 2020SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decompositioncited by 190
  4. 2020BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Imagescited by 166
  5. 2022SAVi++: Towards End-to-End Object-Centric Learning from Real-World Videoscited by 165
  6. 2021Illiterate DALL-E Learns to Composecited by 147
  7. 2018Sequential Attend, Infer, Repeat: Generative Modelling of Moving Objectscited by 128
  8. 2017Neural Expectation Maximizationcited by 123
  9. 2019Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEscited by 116
  10. 2021GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinementcited by 109
  11. 2019SCALOR: Generative World Models with Scalable Object Representationscited by 108
  12. 2019Towards Unsupervised Learning of Generative Models for 3D Controllable Image Synthesiscited by 104
  13. 2023Object-Centric Slot Diffusioncited by 90
  14. 2018Taming VAEscited by 85
  15. 2021Greedy Hierarchical Variational Autoencoders for Large-Scale Video Predictioncited by 75
  16. 2020Generative Neurosymbolic Machinescited by 57
  17. 2018ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stackingcited by 55
  18. 2017Deep Object-Centric Representations for Generalizable Robot Learningcited by 50
  19. 2022Neural Systematic Bindercited by 37
  20. 2021Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representationscited by 36
  21. 2020RELATE: Physically Plausible Multi-Object Scene Synthesis Using Structured Latent Spacescited by 32
  22. 2022Compositional Multi-Object Reinforcement Learning with Linear Relation Networkscited by 19
  23. 2020Reconstruction Bottlenecks in Object-Centric Generative Modelscited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 6; 2025: 8; 2026: 4.

20 papers.

Sort:

By area:

  1. 2024Interaction Asymmetry: A General Principle for Learning Composable Abstractionscited by 19
  2. 2023Grounded Object Centric Learningcited by 17
  3. 2025Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generationcited by 13
  4. 2025Mechanisms of Projective Composition of Diffusion Modelscited by 13
  5. 2024Compositional Image Decomposition with Diffusion Modelscited by 12
  6. 2024Neural Language of Thought Modelscited by 9
  7. 2024Identifiable Object-Centric Representation Learning via Probabilistic Slot Attentioncited by 9
  8. 2024Reasoning-Enhanced Object-Centric Learning for Videoscited by 7
  9. 2024OCK: Unsupervised Dynamic Video Prediction with Object-Centric Kinematicscited by 3
  10. 2025Compositional Scene Understanding through Inverse Generative Modelingcited by 3
  11. 2026Reconstruction-Guided Slot Curriculum: Addressing Object Over-Fragmentation in Video Object-Centric Learningcited by 3
  12. 2023Leveraging Image Augmentation for Object Manipulation: Towards Interpretable Controllability in Object-Centric Learningcited by 1
8 more
  1. 2025Object-Centric Case-Based Reasoning via Argumentationcited by 1
  2. 2026Selective Synergistic Learning for Video Object-Centric Learningcited by 1
  3. 2025Oh-A-DINO: Understanding and Enhancing Attribute-Level Information in Self-Supervised Object-Centric Representationscited by 0
  4. 2025Identifiable Object Representations under Spatial Ambiguitiescited by 0
  5. 2025Cloud Model Characteristic Function Auto-Encoder: Integrating Cloud Model Theory with MMD Regularization for Enhanced Generative Modelingcited by 0
  6. 2025Unsupervised Structural Scene Decomposition via Foreground-Aware Slot Attention with Pseudo-Mask Guidancecited by 0
  7. 2026Meta-probabilistic Modelingcited by 0
  8. 2026Weakly supervised concept Bottleneck Learning for Robust Two stage Object centric visual reasoningcited by 0