Learning Object Arrangements in 3D Scenes using Human Context

TL;DR

This paper introduces a method for arranging objects in 3D scenes by modeling their relationships to human poses, improving scalability and accuracy over traditional object-object models.

Contribution

It proposes a novel approach that models human-object relationships using density functions and a Dirichlet process mixture model for better scene arrangement predictions.

Findings

Achieved an average placement error of 1.6 meters in 20 rooms.

Scored 4.3/5 on real scene arrangements, outperforming baseline methods.

Scalable modeling of human-object relationships improves scene understanding.

Abstract

We consider the problem of learning object arrangements in a 3D scene. The key idea here is to learn how objects relate to human poses based on their affordances, ease of use and reachability. In contrast to modeling object-object relationships, modeling human-object relationships scales linearly in the number of objects. We design appropriate density functions based on 3D spatial features to capture this. We learn the distribution of human poses in a scene using a variant of the Dirichlet process mixture model that allows sharing of the density function parameters across the same object types. Then we can reason about arrangements of the objects in the room based on these meaningful human poses. In our extensive experiments on 20 different rooms with a total of 47 objects, our algorithm predicted correct placements with an average error of 1.6 meters from ground truth. In arranging five real scenes, it received a score of 4.3/5 compared to 3.7 for the best baseline method.