Reviews: Controllable Text-to-Image Generation

This paper was reviewed by three expert reviewers and received three Weak Accept recommendations. After rebuttal, all the reviewers are positive about this paper, and agree that the paper is generally well written, the considered problem is interesting, and the results are impressive. Nevertheless, on the other hand, both R1 and R2 commented that it is difficult to judge the significance of the results due to lack of sufficient ablation studies and the fact that CUB is saturated. Besides, R1 had concerns regarding the novelty of the paper, and R3 left several detailed comments for the authors to deal with. The rebuttal partially solves the reviewers' concerns.