Performance of DEXTR with 2 or 3 points about dextr-pytorch HOT 3 CLOSED

Thanks

It actually works on those long and thin objects, where 2 extreme points are physically close to each others

from dextr-pytorch.

Hello, thanks for the kind words. With 2 or 3 extreme points we are not able to recover the bounding box (in most cases). The bounding box leads to substantial performance improvements (Table 2, first row in the paper).

from dextr-pytorch.

As @kmaninis mentioned it is quite important for our method to use a bounding boxes. If you think you can obtain one from the 2 or 3 extreme points by assuming some parameters ie clicking the top and bottom and assuming always a fix width, then you could give it try!

from dextr-pytorch.