# Learning Densities in Feature Space for Reliable Segmentation of Indoor Scenes

## TL;DR

This paper introduces a novel background modeling approach using normalizing flows to reliably segment foreground objects from background in indoor scenes, improving generalization to unseen objects and enhancing robotic safety.

## Contribution

The paper presents a new method leveraging normalizing flows for background density estimation, enabling reliable foreground-background segmentation without explicit object modeling.

## Key findings

- Effective segmentation of foreground objects in indoor scenes
- Good generalization to out-of-distribution objects
- Potential for safer robotic deployment

## Abstract

Deep learning has enabled remarkable advances in scene understanding, particularly in semantic segmentation tasks. Yet, current state of the art approaches are limited to a closed set of classes, and fail when facing novel elements, also known as out of distribution (OoD) data. This is a problem as autonomous agents will inevitably come across a wide range of objects, all of which cannot be included during training. We propose a novel method to distinguish any object (foreground) from empty building structure (background) in indoor environments. We use normalizing flow to estimate the probability distribution of high-dimensional background descriptors. Foreground objects are therefore detected as areas in an image for which the descriptors are unlikely given the background distribution. As our method does not explicitly learn the representation of individual objects, its performance generalizes well outside of the training examples. Our model results in an innovative solution to reliably segment foreground from background in indoor scenes, which opens the way to a safer deployment of robots in human environments.