Physically-Based Rendering for Indoor Scene Understanding Using Convolutional Neural Networks
arXiv:1612.07429
Abstract
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.
Updates camera ready version. Accepted by CVPR 2017
References in corpus (10)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Multi-Scale Context Aggregation by Dilated Convolutions
- Fully Convolutional Networks for Semantic Segmentation
- Playing for Data: Ground Truth from Computer Games
- Render for CNN: Viewpoint Estimation in Images Using CNNs Trained with Rendered 3D Model Views
- SceneNet: Understanding Real World Indoor Scenes With Synthetic Data
- Semantic Scene Completion from a Single Depth Image
- Understanding deep features with computer-generated imagery
- How useful is photo-realistic rendering for visual learning?
- DeepContext: Context-Encoding Neural Pathways for 3D Holistic Scene Understanding