# Efficient inference in occlusion-aware generative models of images

arXiv: https://arxiv.org/abs/1511.06362 · HTML: https://mlsanity.com/paper/1511.06362/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2015.

## Built on by (most cited first, 11 of 11)

- [GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement](https://mlsanity.com/paper/2104.09958/) (2021)
- [MarioNette: Self-Supervised Sprite Learning](https://mlsanity.com/paper/2104.14553/) (2021)
- [Compositional Scene Representation Learning via Reconstruction: A Survey](https://mlsanity.com/paper/2202.07135/) (2022)
- [Neuromorphic Visual Scene Understanding with Resonator Networks](https://mlsanity.com/paper/2208.12880/) (2022)
- [Promising or Elusive? Unsupervised Object Segmentation from Real-world Single Images](https://mlsanity.com/paper/2210.02324/) (2022)
- [Object-wise Masked Autoencoders for Fast Pre-training](https://mlsanity.com/paper/2205.14338/) (2022)
- [Unsupervised Learning of Compositional Scene Representations from Multiple Unspecified Viewpoints](https://mlsanity.com/paper/2112.03568/) (2021)
- [Knowledge-Guided Object Discovery with Acquired Deep Impressions](https://mlsanity.com/paper/2103.10611/) (2021)
- [Benchmarking and Analysis of Unsupervised Object Segmentation from Real-world Single Images](https://mlsanity.com/paper/2312.04947/) (2023)
- [Unsupervised Object-Centric Learning from Multiple Unspecified Viewpoints](https://mlsanity.com/paper/2401.01922/) (2024)
- [Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomy](https://mlsanity.com/paper/2411.00868/) (2024)

## Abstract (arXiv)

We present a generative model of images based on layering, in which image layers are individually generated, then composited from front to back. We are thus able to factor the appearance of an image into the appearance of individual objects within the image --- and additionally for each individual object, we can factor content from pose. Unlike prior work on layered models, we learn a shape prior for each object/layer, allowing the model to tease out which object is in front by looking for a consistent shape, without needing access to motion cues or any labeled data. We show that ordinary stochastic gradient variational bayes (SGVB), which optimizes our fully differentiable lower-bound on the log-likelihood, is sufficient to learn an interpretable representation of images. Finally we present experiments demonstrating the effectiveness of the model for inferring foreground and background objects in images.