769c3bce651ce5feaa01ce3b75986420-AuthorFeedback.pdf

First of all, we would like to thank the reviewers for their constructive feedback and thorough reviews. In comparison to prior work, our network is more accurate and generalizes better across benchmarks. Table 1 prove that our method is robust to this type of input noise. The remaining "3 of 5" experiments in [7, Figure 1.] that R3 frequently refers to are based on Surreal which is We will state this point more clearly in the paper and thank the reviewer for the insight. According to [7, Appendix C] this leads to problems for humans in "bent over poses", see also Figure 2 of our Appendix.