#######################################################################
#                                                                     #
# Questions for                                                       #
# "DeepIM: Deep Iterative Matching for 6D Pose Estimation"            #
# by Yi Li, Gu Wang, Xiangyang Ji, Yu Xiang, and Dieter Fox           #
#                                                                     #
# Answers due on Thursday **January 17, 2019 at 10am**                #
#         to mayern@cs.uni-freiburg.de                                #
#                                                                     #
#######################################################################

1. In your own words, describe what kind of failure the paragraph 
   beginning at the bottom of page 10 ("The table shows..." until 
   "...ground truth poses") reports. Why should the proposed remedy
   help in this case? (2-4 sentences)

2. "We furthermore show that DeepIM is able to match previously unseen
   objects" (from the abstract). Do you think that this is a noteworthy
   contribution? In other words: had you not read this sentence, would
   you or would you not expect the method to have this property? Why?
   (2-3 sentences)