Domain Randomization for Object Counting
This addresses the need for inexpensive and generalizable synthetic data generation for object counting in various domains, though it is incremental as it builds on existing domain randomization concepts.
The paper tackles the problem of generating synthetic datasets for object counting across diverse domains without expensive photorealism, by using domain randomization with random textures and 3D transformations. Experiments show it achieves good performance on real-world datasets for people, vehicles, penguins, and fruit.
Recently, the use of synthetic datasets based on game engines has been shown to improve the performance of several tasks in computer vision. However, these datasets are typically only appropriate for the specific domains depicted in computer games, such as urban scenes involving vehicles and people. In this paper, we present an approach to generate synthetic datasets for object counting for any domain without the need for photo-realistic techniques manually generated by expensive teams of 3D artists. We introduce a domain randomization approach for object counting based on synthetic datasets that are quick and inexpensive to generate. We deliberately avoid photorealism and drastically increase the variability of the dataset, producing images with random textures and 3D transformations, which improves generalization. Experiments show that our method facilitates good performance on various real word object counting datasets for multiple domains: people, vehicles, penguins, and fruit. The source code is available at: https://github.com/enric1994/dr4oc