NeurIPS 2020

Learning the Geometry of Wave-Based Imaging

Meta Review

All four reviewers participated in the discussion and found the rebuttal somewhat satisfying. Some of the reviewers increased their score. The reviewers agreed that the paper should be accepted as the FIOnet architecture represents a solid contribution. There were also some criticisms about the paper, specially regarding comparison with other methods. I would like to encourage the authors to follow the reviewers' suggestions to improve the camera-ready version. In particular, I strongly encourage the authors to include a comparison against an oracle method as suggested by R4.