Reviews: Attend, Infer, Repeat: Fast Scene Understanding with Generative Models

Technical quality: The technical contribution of the paper is defined at the level of a framework with modular parts and so is quite high-level as a result. The main components are the generative model (Eq 1), the recurrent inference network, and the use of variational learning. To the extent that technical details are provided for these components, they are correct. The bulk of the paper focuses on the construction of experiments and the analysis of the results. In general, the data sets and tasks are well designed in both the 2D and 3D cases.