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

by   Yinda Zhang, et al.

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.


page 1

page 2

page 3

page 4

page 5

page 6

page 7

page 8


SceneNet RGB-D: 5M Photorealistic Images of Synthetic Indoor Trajectories with Ground Truth

We introduce SceneNet RGB-D, expanding the previous work of SceneNet to ...

Configurable, Photorealistic Image Rendering and Ground Truth Synthesis by Sampling Stochastic Grammars Representing Indoor Scenes

We propose the configurable rendering of massive quantities of photoreal...

Procedural Modeling and Physically Based Rendering for Synthetic Data Generation in Automotive Applications

We present an overview and evaluation of a new, systematic approach for ...

Photorealistic Image Synthesis for Object Instance Detection

We present an approach to synthesize highly photorealistic images of 3D ...

TO-Scene: A Large-scale Dataset for Understanding 3D Tabletop Scenes

Many basic indoor activities such as eating or writing are always conduc...

Beyond RGB: Scene-Property Synthesis with Neural Radiance Fields

Comprehensive 3D scene understanding, both geometrically and semanticall...

Floors are Flat: Leveraging Semantics for Real-Time Surface Normal Prediction

We propose 4 insights that help to significantly improve the performance...

Please sign up or login with your details

Forgot password? Click here to reset