# Disentangling Shape and Pose for Object-Centric Deep Active Inference Models

arXiv: https://arxiv.org/abs/2209.09097 · HTML: https://mlsanity.com/paper/2209.09097/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 33 references that are in the map.
- First posted on arXiv 16 Sep 2022.

## Builds on (most cited first, 19 of 19)

- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [ShapeNet: An Information-Rich 3D Model Repository](https://mlsanity.com/paper/1512.03012/) (2015)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [Multimodal Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/1804.04732/) (2018)
- [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018)
- [Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling](https://mlsanity.com/paper/1610.07584/) (2016)
- [Variational Inference of Disentangled Latent Concepts from Unlabeled Observations](https://mlsanity.com/paper/1711.00848/) (2017)
- [Isolating Sources of Disentanglement in Variational Autoencoders](https://mlsanity.com/paper/1802.04942/) (2018)
- [Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction](https://mlsanity.com/paper/1706.07036/) (2017)
- [Are Disentangled Representations Helpful for Abstract Visual Reasoning?](https://mlsanity.com/paper/1905.12506/) (2019)
- [Taming VAEs](https://mlsanity.com/paper/1810.00597/) (2018)
- [Deep active inference agents using Monte-Carlo methods](https://mlsanity.com/paper/2006.04176/) (2020)
- [Active Inference in Robotics and Artificial Agents: Survey and Challenges](https://mlsanity.com/paper/2112.01871/) (2021)
- [Deep Active Inference](https://mlsanity.com/paper/1709.02341/) (2017)
- [End-to-End Pixel-Based Deep Active Inference for Body Perception and Action](https://mlsanity.com/paper/2001.05847/) (2019)
- [The Free Energy Principle for Perception and Action: A Deep Learning Perspective](https://mlsanity.com/paper/2207.06415/) (2022)
- [Disentangling What and Where for 3D Object-Centric Representations Through Active Inference](https://mlsanity.com/paper/2108.11762/) (2021)

## Built on by (most cited first, 6 of 6)

- [Disentangled Representation Learning](https://mlsanity.com/paper/2211.11695/) (2022)
- [Symmetry and Complexity in Object-Centric Deep Active Inference Models](https://mlsanity.com/paper/2304.14493/) (2023)
- [Object-Centric Scene Representations using Active Inference](https://mlsanity.com/paper/2302.03288/) (2023)
- [Measuring the Effect of Causal Disentanglement on the Adversarial Robustness of Neural Network Models](https://mlsanity.com/paper/2308.10708/) (2023)
- [Deep hybrid models: infer and plan in a dynamic world](https://mlsanity.com/paper/2402.10088/) (2024)
- [Dynamic planning in hierarchical active inference](https://mlsanity.com/paper/2402.11658/) (2024)

## Abstract (arXiv)

Active inference is a first principles approach for understanding the brain in particular, and sentient agents in general, with the single imperative of minimizing free energy. As such, it provides a computational account for modelling artificial intelligent agents, by defining the agent's generative model and inferring the model parameters, actions and hidden state beliefs. However, the exact specification of the generative model and the hidden state space structure is left to the experimenter, whose design choices influence the resulting behaviour of the agent. Recently, deep learning methods have been proposed to learn a hidden state space structure purely from data, alleviating the experimenter from this tedious design task, but resulting in an entangled, non-interpreteable state space. In this paper, we hypothesize that such a learnt, entangled state space does not necessarily yield the best model in terms of free energy, and that enforcing different factors in the state space can yield a lower model complexity. In particular, we consider the problem of 3D object representation, and focus on different instances of the ShapeNet dataset. We propose a model that factorizes object shape, pose and category, while still learning a representation for each factor using a deep neural network. We show that models, with best disentanglement properties, perform best when adopted by an active agent in reaching preferred observations.