mlsanityData to 7 Oct 2026

Object-Centric Image Generation with Factored Depths, Locations, and Appearances

arXiv 2004.00642 ↗First posted 1 Apr 2020cs.LG cs.CV stat.MLcited by 20

Not on the map. Why?

Abstract (arXiv)

We present a generative model of images that explicitly reasons over the set of objects they show. Our model learns a structured latent representation that separates objects from each other and from the background; unlike prior works, it explicitly represents the 2D position and depth of each object, as well as an embedding of its segmentation mask and appearance. The model can be trained from images alone in a purely unsupervised fashion without the need for object masks or depth information. Moreover, it always generates complete objects, even though a significant fraction of training images contain occlusions. Finally, we show that our model can infer decompositions of novel images into their constituent objects, including accurate prediction of depth ordering and segmentation of occluded parts.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Apr 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 6; 2022: 5; 2023: 4; 2024: 5.

20 papers.

Sort:

By area:

  1. 2021Illiterate DALL-E Learns to Composecited by 147
  2. 2022Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videoscited by 139
  3. 2021GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinementcited by 109
  4. 2022Object Scene Representation Transformercited by 90
  5. 2023Object-Centric Slot Diffusioncited by 90
  6. 2021SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editingcited by 58
  7. 2021Learning Object-Centric Representations of Multi-Object Scenes from Multiple Viewscited by 37
  8. 2022Neural Systematic Bindercited by 37
  9. 2023Rotating Features for Object Discoverycited by 29
  10. 2021Compositional Transformers for Scene Generationcited by 24
  11. 2024Slot State Space Modelscited by 17
  12. 2022Promising or Elusive? Unsupervised Object Segmentation from Real-world Single Imagescited by 16
8 more
  1. 2024Neural Language of Thought Modelscited by 9
  2. 2023BlobGAN-3D: A Spatially-Disentangled 3D-Aware Generative Model for Indoor Scenescited by 8
  3. 2021Learning Foreground-Background Segmentation from Improved Layered GANscited by 7
  4. 2024Binding Dynamics in Rotating Featurescited by 5
  5. 2023Benchmarking and Analysis of Unsupervised Object Segmentation from Real-world Single Imagescited by 4
  6. 2024Explicitly Disentangled Representations in Object-Centric Learningcited by 4
  7. 2024Parallelized Spatiotemporal Bindingcited by 2
  8. 2022Towards Improving the Generation Quality of Autoregressive Slot VAEscited by 1