The subset of film leads to results very similar to previous work.

Posted: January 20, 2016 at 11:17 am

I thought using a smaller chunk of the film would lead to less abstract results, but that turns out not to be the case. I wanted to try the same method with less frames to see what happens without changing anything else. There is no percept filtering, and percepts are still scaled according to the difference in area between regions and their clusters. See the results below:

store-0001043 store-0001043

store-0001848 store-0001848

store-0003902 store-0003902

store-0000351 store-0000351

store-0009904 store-0009904

The results are still far too abstract. I did a short test without the scaling code and there was an improvement. I’m currently filtering the regions so that only those below a certain threshold area are kept. I need to do another run of clustering and then LUT computation on top of that though, so it may be a couple more days before we see those results.