BIM Hyperreality: Data Synthesis Using BIM and Hyperrealistic Rendering for Deep Learning

TL;DR

This paper introduces a hybrid approach combining BIM and hyperrealistic rendering to generate synthetic datasets for training neural networks in building object recognition, addressing data scarcity in architectural deep learning.

Contribution

It presents a novel method for synthesizing training data using BIM and photorealistic rendering, enabling neural networks to recognize building objects without real photo training data.

Findings

Neural networks trained on synthetic BIM-rendered data can identify building objects in real photos.

The approach reduces the need for manually annotated real-world datasets.

Synthetic data can effectively train deep learning models for architectural visual recognition.

Abstract

Deep learning is expected to offer new opportunities and a new paradigm for the field of architecture. One such opportunity is teaching neural networks to visually understand architectural elements from the built environment. However, the availability of large training datasets is one of the biggest limitations of neural networks. Also, the vast majority of training data for visual recognition tasks is annotated by humans. In order to resolve this bottleneck, we present a concept of a hybrid system using both building information modeling (BIM) and hyperrealistic (photorealistic) rendering to synthesize datasets for training a neural network for building object recognition in photos. For generating our training dataset BIMrAI, we used an existing BIM model and a corresponding photo-realistically rendered model of the same building. We created methods for using renderings to train a deep learning model, trained a generative adversarial network (GAN) model using these methods, and tested the output model on real-world photos. For the specific case study presented in this paper, our results show that a neural network trained with synthetic data; i.e., photorealistic renderings and BIM-based semantic labels, can be used to identify building objects from photos without using photos in the training data. Future work can enhance the presented methods using available BIM models and renderings for more generalized mapping and description of photographed built environments.