SuperCaustics: Real-time, open-source simulation of transparent objects for deep learning applications

TL;DR

SuperCaustics is a real-time, open-source simulation tool for transparent objects that enhances deep learning training by accurately modeling caustics, refraction, and dispersion, leading to improved segmentation performance with less data.

Contribution

We introduce SuperCaustics, a novel simulation framework that generates realistic transparent object datasets with complex optical effects for deep learning.

Findings

Neural network trained with SuperCaustics data performs comparably to state-of-the-art on real data.

Models trained with SuperCaustics can segment various caustic effects, even with overlapping objects.

Achieves high accuracy using only 10% of the training data and faster training times.

Abstract

Transparent objects are a very challenging problem in computer vision. They are hard to segment or classify due to their lack of precise boundaries, and there is limited data available for training deep neural networks. As such, current solutions for this problem employ rigid synthetic datasets, which lack flexibility and lead to severe performance degradation when deployed on real-world scenarios. In particular, these synthetic datasets omit features such as refraction, dispersion and caustics due to limitations in the rendering pipeline. To address this issue, we present SuperCaustics, a real-time, open-source simulation of transparent objects designed for deep learning applications. SuperCaustics features extensive modules for stochastic environment creation; uses hardware ray-tracing to support caustics, dispersion, and refraction; and enables generating massive datasets with multi-modal, pixel-perfect ground truth annotations. To validate our proposed system, we trained a deep neural network from scratch to segment transparent objects in difficult lighting scenarios. Our neural network achieved performance comparable to the state-of-the-art on a real-world dataset using only 10% of the training data and in a fraction of the training time. Further experiments show that a model trained with SuperCaustics can segment different types of caustics, even in images with multiple overlapping transparent objects. To the best of our knowledge, this is the first such result for a model trained on synthetic data. Both our open-source code and experimental data are freely available online.