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

arXiv: https://arxiv.org/abs/2004.00642 · HTML: https://mlsanity.com/paper/2004.00642/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Apr 2020.

## Built on by (most cited first, 20 of 20)

- [Illiterate DALL-E Learns to Compose](https://mlsanity.com/paper/2110.11405/) (2021)
- [Simple Unsupervised Object-Centric Learning for Complex and Naturalistic Videos](https://mlsanity.com/paper/2205.14065/) (2022)
- [GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement](https://mlsanity.com/paper/2104.09958/) (2021)
- [Object Scene Representation Transformer](https://mlsanity.com/paper/2206.06922/) (2022)
- [Object-Centric Slot Diffusion](https://mlsanity.com/paper/2303.10834/) (2023)
- [SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing](https://mlsanity.com/paper/2112.02236/) (2021)
- [Learning Object-Centric Representations of Multi-Object Scenes from Multiple Views](https://mlsanity.com/paper/2111.07117/) (2021)
- [Neural Systematic Binder](https://mlsanity.com/paper/2211.01177/) (2022)
- [Rotating Features for Object Discovery](https://mlsanity.com/paper/2306.00600/) (2023)
- [Compositional Transformers for Scene Generation](https://mlsanity.com/paper/2111.08960/) (2021)
- [Slot State Space Models](https://mlsanity.com/paper/2406.12272/) (2024)
- [Promising or Elusive? Unsupervised Object Segmentation from Real-world Single Images](https://mlsanity.com/paper/2210.02324/) (2022)
- [Neural Language of Thought Models](https://mlsanity.com/paper/2402.01203/) (2024)
- [BlobGAN-3D: A Spatially-Disentangled 3D-Aware Generative Model for Indoor Scenes](https://mlsanity.com/paper/2303.14706/) (2023)
- [Learning Foreground-Background Segmentation from Improved Layered GANs](https://mlsanity.com/paper/2104.00483/) (2021)
- [Binding Dynamics in Rotating Features](https://mlsanity.com/paper/2402.05627/) (2024)
- [Benchmarking and Analysis of Unsupervised Object Segmentation from Real-world Single Images](https://mlsanity.com/paper/2312.04947/) (2023)
- [Explicitly Disentangled Representations in Object-Centric Learning](https://mlsanity.com/paper/2401.10148/) (2024)
- [Parallelized Spatiotemporal Binding](https://mlsanity.com/paper/2402.17077/) (2024)
- [Towards Improving the Generation Quality of Autoregressive Slot VAEs](https://mlsanity.com/paper/2206.01370/) (2022)

## 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.