# Spatial Mixture Models with Learnable Deep Priors for Perceptual Grouping

## TL;DR

This paper introduces a novel spatial mixture model with learnable deep priors that disentangles shape and appearance attributes for perceptual grouping, outperforming existing methods and generalizing well to new scenes.

## Contribution

It proposes a new spatial mixture model with learnable priors that separately model shape and appearance, improving perceptual grouping performance.

## Key findings

- Outperforms state-of-the-art methods on perceptual grouping datasets.
- Learned entities generalize to novel scenes and are robust to object diversity.
- Model effectively disentangles shape and appearance attributes.

## Abstract

Humans perceive the seemingly chaotic world in a structured and compositional way with the prerequisite of being able to segregate conceptual entities from the complex visual scenes. The mechanism of grouping basic visual elements of scenes into conceptual entities is termed as perceptual grouping. In this work, we propose a new type of spatial mixture models with learnable priors for perceptual grouping. Different from existing methods, the proposed method disentangles the attributes of an object into ``shape'' and ``appearance'' which are modeled separately by the mixture weights and the mixture components. More specifically, each object in the visual scene is fully characterized by one latent representation, which is in turn transformed into parameters of the mixture weight and the mixture component by two neural networks. The mixture weights focus on modeling spatial dependencies (i.e., shape) and the mixture components deal with intra-object variations (i.e., appearance). In addition, the background is separately modeled as a special component complementary to the foreground objects. Our extensive empirical tests on two perceptual grouping datasets demonstrate that the proposed method outperforms the state-of-the-art methods under most experimental configurations. The learned conceptual entities are generalizable to novel visual scenes and insensitive to the diversity of objects. Code is available at https://github.com/jinyangyuan/learnable-deep-priors.