Re:3D Ken Burns Effect from a Single Image
by sniklaus on Sunday September 15, 2019 @05:09PM
(#20979505)
There definitely is room for improvement. Our proposed framework uses Mask R-CNN for object segmentation. However, Mask R-CNN only as a resolution of 28x28 pixels for the object masks if I remember correctly (which is then resized to the actual resolution of the object in the image). So there are a lot of limitations from that alone.
if you haven't already seen it, https://github.com/dbolya/yolact generates very sharp instance masks very quickly, may be of interest
I thought maybe it grabbed it because it was the same color as the bouquet she is holding, but that is entirely within the white of her dress.