mlsanityData to 7 Oct 2026

Object-Centric Slot Diffusion

arXiv 2303.10834 ↗First posted 20 Mar 2023cs.CV cs.LGcited by 90

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

The recent success of transformer-based image generative models in object-centric learning highlights the importance of powerful image generators for handling complex scenes. However, despite the high expressiveness of diffusion models in image generation, their integration into object-centric learning remains largely unexplored in this domain. In this paper, we explore the feasibility and potential of integrating diffusion models into object-centric learning and investigate the pros and cons of this approach. We introduce Latent Slot Diffusion (LSD), a novel model that serves dual purposes: it is the first object-centric learning model to replace conventional slot decoders with a latent diffusion model conditioned on object slots, and it is also the first unsupervised compositional conditional diffusion model that operates without the need for supervised annotations like text. Through experiments on various object-centric tasks, including the first application of the FFHQ dataset in this field, we demonstrate that LSD significantly outperforms state-of-the-art transformer-based decoders, particularly in more complex scenes, and exhibits superior unsupervised compositional generation quality. In addition, we conduct a preliminary investigation into the integration of pre-trained diffusion models in LSD and demonstrate its effectiveness in real-world image segmentation and generation. Project page is available at https://latentslotdiffusion.github.io

Key facts. Cited by 90 papers in the map (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 67 of its 86 references that are in the map. First posted on arXiv 20 Mar 2023.

Builds on

67 of 86 references.

Closest ancestors · 7

Same direction, newest first

  1. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models16 Feb
  2. 2023Adding Conditional Control to Text-to-Image Diffusion Models10 Feb
  3. 2023GLIGEN: Open-Set Grounded Text-to-Image Generation17 Jan
  4. 2022Compositional Visual Generation with Composable Diffusion Models3 Jun
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  6. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr
  7. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models20 Dec

Other references · 60

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  8. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  9. 2022Classifier-Free Diffusion Guidancecited by 5,717
  10. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  11. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  12. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
38 more
  1. 2021Image Super-Resolution via Iterative Refinementcited by 1,506
  2. 2016CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoningcited by 1,445
  3. 2021Cascaded Diffusion Models for High Fidelity Image Generationcited by 1,155
  4. 2020Object-Centric Learning with Slot Attentioncited by 865
  5. 2018Disentangling by Factorisingcited by 614
  6. 2021Label-Efficient Semantic Segmentation with Diffusion Modelscited by 495
  7. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representationcited by 447
  8. 2019MONet: Unsupervised Scene Decomposition and Representationcited by 388
  9. 2022Kubric: A scalable dataset generatorcited by 373
  10. 2019Multi-Object Representation Learning with Iterative Variational Inferencecited by 359
  11. 2021Conditional Object-Centric Learning from Videocited by 247
  12. 2017Variational Inference of Disentangled Latent Concepts from Unlabeled Observationscited by 240
  13. 2020On the Binding Problem in Artificial Neural Networkscited by 230
  14. 2019GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representationscited by 227
  15. 2022Bridging the Gap to Real-World Object-Centric Learningcited by 219
  16. 2016Attend, Infer, Repeat: Fast Scene Understanding with Generative Modelscited by 209
  17. 2020SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decompositioncited by 190
  18. 2023Cut and Learn for Unsupervised Object Detection and Instance Segmentationcited by 186
  19. 2021Illiterate DALL-E Learns to Composecited by 147
  20. 2022SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Modelscited by 146
  21. 2022Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videoscited by 139
  22. 2017Neural Expectation Maximizationcited by 123
  23. 2021GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinementcited by 109
  24. 2019SCALOR: Generative World Models with Scalable Object Representationscited by 108
  25. 2021ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentationcited by 93
  26. 2022Object Scene Representation Transformercited by 90
  27. 2021Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentationcited by 88
  28. 2021Generalization and Robustness Implications in Object-Centric Learningcited by 81
  29. 2022Object discovery and representation networkscited by 80
  30. 2021Unsupervised Learning of Compositional Energy Conceptscited by 71
  31. 2020Improving Generative Imagination in Object-Centric World Modelscited by 70
  32. 2022Self-Supervised Visual Representation Learning with Semantic Groupingcited by 70
  33. 2021SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decompositioncited by 69
  34. 2020Generative Neurosymbolic Machinescited by 57
  35. 2023An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learningcited by 49
  36. 2022Object Representations as Fixed Points: Training Iterative Refinement Algorithms with Implicit Differentiationcited by 46
  37. 2020ROOTS: Object-Centric Representation and Rendering of 3D Scenescited by 40
  38. 2022Complex-Valued Autoencoders for Object Discoverycited by 40

50 most cited of 60 All 60 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 12; 2024: 31; 2025: 27; 2026: 20.

90 papers.

Sort:

By area:

  1. 2023SlotDiffusion: Object-Centric Generative Modeling with Diffusion Modelscited by 85
  2. 2023Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similaritiescited by 78
  3. 2023SODA: Bottleneck Diffusion Models for Representation Learningcited by 76
  4. 2023SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformerscited by 49
  5. 2024PRDP: Proximal Reward Difference Prediction for Large-Scale Reward Finetuning of Diffusion Modelscited by 41
  6. 2024Artificial Kuramoto Oscillatory Neuronscited by 37
  7. 2024Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Modelscited by 30
  8. 2024What is the Visual Cognition Gap between Humans and Multimodal LLMs?cited by 30
  9. 2024MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editingcited by 30
  10. 2024Temporally Consistent Object-Centric Learning by Contrasting Slotscited by 30
  11. 2023Rotating Features for Object Discoverycited by 29
  12. 2024Diffusion Model with Cross Attention as an Inductive Bias for Disentanglementcited by 27
38 more
  1. 2023Slot-VAE: Object-Centric Scene Generation with Slot Attentioncited by 20
  2. 2023Systematic Visual Reasoning through Object-Centric Relational Abstractioncited by 19
  3. 2024Zero-Shot Object-Centric Representation Learningcited by 19
  4. 2025Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?cited by 19
  5. 2024Slot State Space Modelscited by 17
  6. 2023DORSal: Diffusion for Object-centric Representations of Scenes et alcited by 16
  7. 2023Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Surveycited by 16
  8. 2024Layout Agnostic Scene Text Image Synthesis with Diffusion Modelscited by 14
  9. 2024Exploring the Effectiveness of Object-Centric Representations in Visual Question Answering: Comparative Insights with Foundation Modelscited by 14
  10. 2024GLASS: Guided Latent Slot Diffusion for Object-Centric Learningcited by 14
  11. 2024Learning to Compose: Improving Object Centric Learning by Injecting Compositionalitycited by 13
  12. 2025Slot-Guided Adaptation of Pre-trained Diffusion Models for Object-Centric Learning and Compositional Generationcited by 13
  13. 2025PlaySlot: Learning Inverse Latent Dynamics for Controllable Object-Centric Video Prediction and Planningcited by 13
  14. 2025CTRL-O: Language-Controllable Object-Centric Visual Representation Learningcited by 12
  15. 2025Dyn-O: Building Structured World Models with Object-Centric Representationscited by 12
  16. 2025Vector-Quantized Vision Foundation Models for Object-Centric Learningcited by 11
  17. 2025MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learningcited by 11
  18. 2025Learning Interactive World Model for Object-Centric Reinforcement Learningcited by 11
  19. 2024Slot Abstractors: Toward Scalable Abstract Visual Reasoningcited by 10
  20. 2025Are We Done with Object-Centric Learning?cited by 10
  21. 2023Guided Diffusion from Self-Supervised Diffusion Featurescited by 9
  22. 2024Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learningcited by 9
  23. 2024SkiLD: Unsupervised Skill Discovery Guided by Factor Interactionscited by 9
  24. 2024TIV-Diffusion: Towards Object-Centric Movement for Text-driven Image to Video Generationcited by 7
  25. 2025Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLMcited by 7
  26. 2024Multi-Scale Fusion for Object Representationcited by 6
  27. 2024Bootstrapping Top-down Information for Self-modulating Slot Attentioncited by 6
  28. 2025Object-Centric Pretraining via Target Encoder Bootstrappingcited by 6
  29. 2025Object-Centric Representations Improve Policy Generalization in Robot Manipulationcited by 6
  30. 2026Factored Latent Action World Modelscited by 6
  31. 2024Binding Dynamics in Rotating Featurescited by 5
  32. 2024Grouped Discrete Representation for Object-Centric Learningcited by 5
  33. 2025Smoothing Slot Attention Iterations and Recurrencescited by 5
  34. 2023Im-Promptu: In-Context Composition from Image Promptscited by 4
  35. 2023Associative Transformercited by 4
  36. 2025Slot-BERT: Self-supervised Object Discovery in Surgical Videocited by 4
  37. 2025Dreamweaver: Learning Compositional World Models from Pixelscited by 4
  38. 2025Motion-Refined DINOSAUR for Unsupervised Multi-Object Discoverycited by 4

50 most cited of 90 All 90 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Learning Object-Centric Representations Based on Slots in Real World Scenarios
  2. 2025Conditional Latent Diffusion Models for Zero-Shot Instance Segmentation
  3. 2024Diffusion Models Need Visual Priors for Image Generation
  4. 2022Exploring Transformer Backbones for Image Diffusion Models
  5. 2024GLoD: Composing Global Contexts and Local Details in Image Generation
  6. 2026When Do Diffusion Models learn to Generate Multiple Objects?
  7. 2025Lavida-O: Elastic Large Masked Diffusion Models for Unified Multimodal Understanding and Generation
  8. 2025Boosting Generative Image Modeling via Joint Image-Feature Synthesis