NeurIPS 2019
Sun Dec 8th through Sat the 14th, 2019 at Vancouver Convention Center
Paper ID:2179
Title:PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graph


		
This submission received borderline positive reviews. While the reviewers ultimately did not reach consensus during the discussion period, one did step forward to 'champion' the paper, and another was supportive of this decision. This submission is a 'systems paper,' and should be evaluated as such. The paper does not focus on new algorithmic results, but rather on building a nontrivial system to achieve impressive results on an important problem, and it justifies its design decisions (e.g. with an ablation study). There is some concern about the output images being low-resolution. However, the authors convincingly argue in their response that there exist techniques that could be adapted to their setting for increasing the output resolution, and that this should be viewed as orthogonal to their contribution. Finally, the paper *does* actually include a novel technical contribution, which is in its module for selecting appropriate object crops.