mlsanityData to 14 Oct 2026

GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations

arXiv 1907.13052 ↗First posted 30 Jul 2019cs.LG cs.CV cs.NEcited by 227

Not on the map. Why?

Abstract (arXiv)

Generative latent-variable models are emerging as promising tools in robotics and reinforcement learning. Yet, even though tasks in these domains typically involve distinct objects, most state-of-the-art generative models do not explicitly capture the compositional nature of visual scenes. Two recent exceptions, MONet and IODINE, decompose scenes into objects in an unsupervised fashion. Their underlying generative processes, however, do not account for component interactions. Hence, neither of them allows for principled sampling of novel scenes. Here we present GENESIS, the first object-centric generative model of 3D visual scenes capable of both decomposing and generating scenes by capturing relationships between scene components. GENESIS parameterises a spatial GMM over images which is decoded from a set of object-centric latent variables that are either inferred sequentially in an amortised fashion or sampled from an autoregressive prior. We train GENESIS on several publicly available datasets and evaluate its performance on scene generation, decomposition, and semi-supervised learning.

Key facts. Cited by 227 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Jul 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 53; 2022: 55; 2023: 45; 2024: 34; 2025: 22; 2026: 18.

227 papers.

Sort:

By area:

  1. 2022Kubric: A scalable dataset generatorcited by 381
  2. 2021Conditional Object-Centric Learning from Videocited by 248
  3. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 230
  4. 2022Bridging the Gap to Real-World Object-Centric Learningcited by 220
  5. 2021D'ya like DAGs? A Survey on Structure Learning and Causal Discoverycited by 211
  6. 2022Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localizationcited by 150
  7. 2021Self-supervised Video Object Segmentation by Motion Groupingcited by 147
  8. 2021Illiterate DALL-E Learns to Composecited by 147
  9. 2022Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videoscited by 139
  10. 2021Generative Adversarial Transformerscited by 120
  11. 2021NeRF-VAE: A Geometry Aware 3D Scene Generative Modelcited by 112
  12. 2021GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinementcited by 109
38 more
  1. 2021Unsupervised Discovery of Object Radiance Fieldscited by 101
  2. 2021ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentationcited by 93
  3. 2023Object-Centric Slot Diffusioncited by 90
  4. 2025Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Modelscited by 90
  5. 2021Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentationcited by 88
  6. 2023SlotDiffusion: Object-Centric Generative Modeling with Diffusion Modelscited by 85
  7. 2021Generalization and Robustness Implications in Object-Centric Learningcited by 81
  8. 2022Adversarial Masking for Self-Supervised Learningcited by 78
  9. 2021Neural Production Systems: Learning Rule-Governed Visual Dynamicscited by 75
  10. 2021Greedy Hierarchical Variational Autoencoders for Large-Scale Video Predictioncited by 75
  11. 2021Unsupervised Learning of Compositional Energy Conceptscited by 71
  12. 2022Self-Supervised Visual Representation Learning with Semantic Groupingcited by 70
  13. 2021SIMONe: View-Invariant, Temporally-Abstracted Object Representations via Unsupervised Video Decompositioncited by 69
  14. 2022Active Learning by Feature Mixingcited by 63
  15. 2022Segmenting Moving Objects via an Object-Centric Layered Representationcited by 63
  16. 2022Improving Object-centric Learning with Query Optimizationcited by 60
  17. 2023Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolationcited by 58
  18. 2021Unsupervised Part Discovery from Contrastive Reconstructioncited by 57
  19. 2021Large-Scale Unsupervised Object Discoverycited by 54
  20. 2022Discovering Object Masks with Transformers for Unsupervised Semantic Segmentationcited by 54
  21. 2022Unsupervised Semantic Segmentation with Self-supervised Object-centric Representationscited by 54
  22. 2022Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systemscited by 51
  23. 2023Invariant Slot Attention: Object Discovery with Slot-Centric Reference Framescited by 51
  24. 2021Unsupervised Layered Image Decomposition into Object Prototypescited by 50
  25. 2023An Investigation into Pre-Training Object-Centric Representations for Reinforcement Learningcited by 49
  26. 2023Self-supervised Object-Centric Learning for Videoscited by 49
  27. 2023SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformerscited by 49
  28. 2023Provably Learning Object-Centric Representationscited by 45
  29. 2022Discovering Objects that Can Movecited by 44
  30. 2022Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motioncited by 42
  31. 2022Complex-Valued Autoencoders for Object Discoverycited by 40
  32. 2023Amodal Completion via Progressive Mixed Context Diffusioncited by 38
  33. 2022Neural Systematic Bindercited by 37
  34. 2021Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representationscited by 36
  35. 2022PartAfford: Part-level Affordance Discovery from 3D Objectscited by 36
  36. 2021From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligencecited by 35
  37. 2024Adaptive Slot Attention: Object Discovery with Dynamic Slot Numbercited by 34
  38. 2022VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programmingcited by 31

50 most cited of 227 All 227 (JSON)