SPACE: A Simulator for Physical Interactions and Causal Learning in 3D Environments
This addresses a gap in AI research for more realistic physical causal reasoning datasets, though it is incremental as it builds on existing synthetic dataset methods.
The authors tackled the scarcity of datasets for physical interactions resembling daily human activities by introducing SPACE, a simulator and synthetic video dataset for 3D environments, which improved learning of intuitive physics in a state-of-the-art model through curriculum-inspired approaches.
Recent advancements in deep learning, computer vision, and embodied AI have given rise to synthetic causal reasoning video datasets. These datasets facilitate the development of AI algorithms that can reason about physical interactions between objects. However, datasets thus far have primarily focused on elementary physical events such as rolling or falling. There is currently a scarcity of datasets that focus on the physical interactions that humans perform daily with objects in the real world. To address this scarcity, we introduce SPACE: A Simulator for Physical Interactions and Causal Learning in 3D Environments. The SPACE simulator allows us to generate the SPACE dataset, a synthetic video dataset in a 3D environment, to systematically evaluate physics-based models on a range of physical causal reasoning tasks. Inspired by daily object interactions, the SPACE dataset comprises videos depicting three types of physical events: containment, stability and contact. These events make up the vast majority of the basic physical interactions between objects. We then further evaluate it with a state-of-the-art physics-based deep model and show that the SPACE dataset improves the learning of intuitive physics with an approach inspired by curriculum learning. Repository: https://github.com/jiafei1224/SPACE