# Hierarchy Denoising Recursive Autoencoders for 3D Scene Layout Prediction

arXiv: https://arxiv.org/abs/1903.03757 · HTML: https://mlsanity.com/paper/1903.03757/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Mar 2019.

## Built on by (most cited first, 8 of 8)

- [Graph-to-3D: End-to-End Generation and Manipulation of 3D Scenes Using Scene Graphs](https://mlsanity.com/paper/2108.08841/) (2021)
- [SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation with Fine-Grained Geometry](https://mlsanity.com/paper/2302.10237/) (2023)
- [MaskGroup: Hierarchical Point Grouping and Masking for 3D Instance Segmentation](https://mlsanity.com/paper/2203.14662/) (2022)
- [ARM3D: Attention-based relation module for indoor 3D object detection](https://mlsanity.com/paper/2202.09715/) (2022)
- [The Neurally-Guided Shape Parser: Grammar-based Labeling of 3D Shape Regions with Approximate Inference](https://mlsanity.com/paper/2106.12026/) (2021)
- [DisARM: Displacement Aware Relation Module for 3D Detection](https://mlsanity.com/paper/2203.01152/) (2022)
- [3DRM:Pair-wise relation module for 3D object detection](https://mlsanity.com/paper/2202.09721/) (2022)
- [CMR3D: Contextualized Multi-Stage Refinement for 3D Object Detection](https://mlsanity.com/paper/2209.06641/) (2022)

## Abstract (arXiv)

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.