# Reconstruction Bottlenecks in Object-Centric Generative Models

arXiv: https://arxiv.org/abs/2007.06245 · HTML: https://mlsanity.com/paper/2007.06245/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jul 2020.

## Built on by (most cited first, 17 of 17)

- [GENESIS-V2: Inferring Unordered Object Representations without Iterative Refinement](https://mlsanity.com/paper/2104.09958/) (2021)
- [Generalization and Robustness Implications in Object-Centric Learning](https://mlsanity.com/paper/2107.00637/) (2021)
- [Provably Learning Object-Centric Representations](https://mlsanity.com/paper/2305.14229/) (2023)
- [Guess What Moves: Unsupervised Video and Image Segmentation by Anticipating Motion](https://mlsanity.com/paper/2205.07844/) (2022)
- [PartAfford: Part-level Affordance Discovery from 3D Objects](https://mlsanity.com/paper/2202.13519/) (2022)
- [Slot-VAE: Object-Centric Scene Generation with Slot Attention](https://mlsanity.com/paper/2306.06997/) (2023)
- [Composing Pre-Trained Object-Centric Representations for Robotics From "What" and "Where" Foundation Models](https://mlsanity.com/paper/2404.13474/) (2024)
- [Inductive Biases for Object-Centric Representations in the Presence of Complex Textures](https://mlsanity.com/paper/2204.08479/) (2022)
- [Test-time Adaptation with Slot-Centric Models](https://mlsanity.com/paper/2203.11194/) (2022)
- [Benchmarks for Physical Reasoning AI](https://mlsanity.com/paper/2312.10728/) (2023)
- [Recasting Generic Pretrained Vision Transformers As Object-Centric Scene Encoders For Manipulation Policies](https://mlsanity.com/paper/2405.15916/) (2024)
- [Latent Noise Segmentation: How Neural Noise Leads to the Emergence of Segmentation and Grouping](https://mlsanity.com/paper/2309.16515/) (2023)
- [ObPose: Leveraging Pose for Object-Centric Scene Inference and Generation in 3D](https://mlsanity.com/paper/2206.03591/) (2022)
- [Object Pursuit: Building a Space of Objects via Discriminative Weight Generation](https://mlsanity.com/paper/2112.07954/) (2021)
- [Ablation Study to Clarify the Mechanism of Object Segmentation in Multi-Object Representation Learning](https://mlsanity.com/paper/2310.03273/) (2023)
- [Simplified priors for Object-Centric Learning](https://mlsanity.com/paper/2410.00728/) (2024)
- [Variational Inference for Scalable 3D Object-centric Learning](https://mlsanity.com/paper/2309.14010/) (2023)

## Abstract (arXiv)

A range of methods with suitable inductive biases exist to learn interpretable object-centric representations of images without supervision. However, these are largely restricted to visually simple images; robust object discovery in real-world sensory datasets remains elusive. To increase the understanding of such inductive biases, we empirically investigate the role of "reconstruction bottlenecks" for scene decomposition in GENESIS, a recent VAE-based model. We show such bottlenecks determine reconstruction and segmentation quality and critically influence model behaviour.