Review for NeurIPS paper: SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images

Weaknesses: - The dependence on the camera pose somewhat limits the applicability. It also raises the question how much the proposed method relies on high quality camera poses. Similarly, it relies on high quality silhouette images and it is not quite clear how robust the method would be in practical setups with silhouettes coming from e.g. an instance segmentation algorithm. An experiment with different levels of noise for the camera parameters and less than perfect silhouettes would be helpful to asses the robustness in real-world settings. Other work directly optimized the MLPs or conditioned predictions from the MLPs via latent codes. I would suspect those approaches to be more robust than a network predicting network weights.