Hierarchy Denoising Recursive Autoencoders for 3D Scene Layout Prediction

TL;DR

This paper introduces a variational denoising recursive autoencoder that models the hierarchical structure of 3D indoor scenes, improving object detection and segmentation accuracy from point cloud data.

Contribution

The novel VDRAE architecture effectively captures hierarchical context in 3D scenes, enhancing detection and segmentation performance over previous methods.

Findings

Improved object detection accuracy on real-world 3D datasets.

Effective hierarchical representation of 3D scene layouts.

Enhanced segmentation results from point cloud data.

Abstract

Indoor scenes exhibit rich hierarchical structure in 3D object layouts. Many tasks in 3D scene understanding can benefit from reasoning jointly about the hierarchical context of a scene, and the identities of objects. We present a variational denoising recursive autoencoder (VDRAE) that generates and iteratively refines a hierarchical representation of 3D object layouts, interleaving bottom-up encoding for context aggregation and top-down decoding for propagation. We train our VDRAE on large-scale 3D scene datasets to predict both instance-level segmentations and a 3D object detections from an over-segmentation of an input point cloud. We show that our VDRAE improves object detection performance on real-world 3D point cloud datasets compared to baselines from prior work.