# Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networks

arXiv: https://arxiv.org/abs/1612.07429 · HTML: https://mlsanity.com/paper/1612.07429/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2016.

## Built on by (most cited first, 30 of 35)

- [DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision](https://mlsanity.com/paper/2312.16256/) (2023)
- [Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans](https://mlsanity.com/paper/2110.04994/) (2021)
- [Infinite Photorealistic Worlds using Procedural Generation](https://mlsanity.com/paper/2306.09310/) (2023)
- [Learning-based Inverse Rendering of Complex Indoor Scenes with Differentiable Monte Carlo Raytracing](https://mlsanity.com/paper/2211.03017/) (2022)
- [IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenes](https://mlsanity.com/paper/2206.08423/) (2022)
- [Human-Aware Object Placement for Visual Environment Reconstruction](https://mlsanity.com/paper/2203.03609/) (2022)
- [Shape from Polarization for Complex Scenes in the Wild](https://mlsanity.com/paper/2112.11377/) (2021)
- [Planar Surface Reconstruction from Sparse Views](https://mlsanity.com/paper/2103.14644/) (2021)
- [A Review of Deep Learning for Video Captioning](https://mlsanity.com/paper/2304.11431/) (2023)
- [Neural-Sim: Learning to Generate Training Data with NeRF](https://mlsanity.com/paper/2207.11368/) (2022)
- [Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation](https://mlsanity.com/paper/2303.11329/) (2023)
- [AsymFormer: Asymmetrical Cross-Modal Representation Learning for Mobile Platform Real-Time RGB-D Semantic Segmentation](https://mlsanity.com/paper/2309.14065/) (2023)
- [360 Depth Estimation in the Wild -- The Depth360 Dataset and the SegFuse Network](https://mlsanity.com/paper/2202.08010/) (2022)
- [Spatially-Varying Outdoor Lighting Estimation from Intrinsics](https://mlsanity.com/paper/2104.04160/) (2021)
- [Adaptive Surface Normal Constraint for Geometric Estimation from Monocular Images](https://mlsanity.com/paper/2402.05869/) (2024)
- [Unsupervised Kinematic Motion Detection for Part-segmented 3D Shape Collections](https://mlsanity.com/paper/2206.08497/) (2022)
- [Generating Diverse Agricultural Data for Vision-Based Farming Applications](https://mlsanity.com/paper/2403.18351/) (2024)
- [DeRenderNet: Intrinsic Image Decomposition of Urban Scenes with Shape-(In)dependent Shading Rendering](https://mlsanity.com/paper/2104.13602/) (2021)
- [Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap](https://mlsanity.com/paper/2203.03833/) (2022)
- [SIMPL: Generating Synthetic Overhead Imagery to Address Zero-shot and Few-Shot Detection Problems](https://mlsanity.com/paper/2106.15681/) (2021)
- [Transferable End-to-end Room Layout Estimation via Implicit Encoding](https://mlsanity.com/paper/2112.11340/) (2021)
- [Variational Structured Attention Networks for Deep Visual Representation Learning](https://mlsanity.com/paper/2103.03510/) (2021)
- [Normal Transformer: Extracting Surface Geometry from LiDAR Points Enhanced by Visual Semantics](https://mlsanity.com/paper/2211.10580/) (2022)
- [Synthetic Image Data for Deep Learning](https://mlsanity.com/paper/2212.06232/) (2022)
- [MatPredict: a dataset and benchmark for learning material properties of diverse indoor objects](https://mlsanity.com/paper/2505.13201/) (2025)
- [BIM Hyperreality: Data Synthesis Using BIM and Hyperrealistic Rendering for Deep Learning](https://mlsanity.com/paper/2105.04103/) (2021)
- [MINERVAS: Massive INterior EnviRonments VirtuAl Synthesis](https://mlsanity.com/paper/2107.06149/) (2021)
- [Monocular Depth Estimation Primed by Salient Point Detection and Normalized Hessian Loss](https://mlsanity.com/paper/2108.11098/) (2021)
- [Roominoes: Generating Novel 3D Floor Plans From Existing 3D Rooms](https://mlsanity.com/paper/2112.05644/) (2021)
- [Meta-simulation for the Automated Design of Synthetic Overhead Imagery](https://mlsanity.com/paper/2209.08685/) (2022)

## Abstract (arXiv)

Indoor scene understanding is central to applications such as robot navigation and human companion assistance. Over the last years, data-driven deep neural networks have outperformed many traditional approaches thanks to their representation learning capabilities. One of the bottlenecks in training for better representations is the amount of available per-pixel ground truth data that is required for core scene understanding tasks such as semantic segmentation, normal prediction, and object edge detection. To address this problem, a number of works proposed using synthetic data. However, a systematic study of how such synthetic data is generated is missing. In this work, we introduce a large-scale synthetic dataset with 400K physically-based rendered images from 45K realistic 3D indoor scenes. We study the effects of rendering methods and scene lighting on training for three computer vision tasks: surface normal prediction, semantic segmentation, and object boundary detection. This study provides insights into the best practices for training with synthetic data (more realistic rendering is worth it) and shows that pretraining with our new synthetic dataset can improve results beyond the current state of the art on all three tasks.