# 3D-RelNet: Joint Object and Relational Network for 3D Prediction

## TL;DR

This paper introduces 3D-RelNet, a novel framework that jointly predicts 3D object shapes, poses, and their relationships to enhance accuracy in 3D scene understanding.

## Contribution

It presents a method to incorporate pairwise object relationships into 3D prediction, improving over independent object prediction approaches.

## Key findings

- Significant performance improvement over independent prediction methods.
- Effective incorporation of pairwise relations enhances 3D shape and pose estimation.
- Outperforms existing implicit reasoning approaches on multiple datasets.

## Abstract

We propose an approach to predict the 3D shape and pose for the objects present in a scene. Existing learning based methods that pursue this goal make independent predictions per object, and do not leverage the relationships amongst them. We argue that reasoning about these relationships is crucial, and present an approach to incorporate these in a 3D prediction framework. In addition to independent per-object predictions, we predict pairwise relations in the form of relative 3D pose, and demonstrate that these can be easily incorporated to improve object level estimates. We report performance across different datasets (SUNCG, NYUv2), and show that our approach significantly improves over independent prediction approaches while also outperforming alternate implicit reasoning methods.