-
It isn't initially obvious that the badge on the Review button indicates number of reviewed superpixels. We should add a tooltip to that effect.
Also, maybe it is just me, but I feel that having a…
-
I could not train properly. I used opencv-python3.4.0.14 to Extract the superpixels and line segments, but the problem still occurred.
Training model named:
mdp
Models and tensorboard events f…
-
Does the file named compute_spixels.py generate superpixels and the file named compute_segment.py generate segmentation?
-
Instead of implementing k-means clustering on the pixels of an image itself, it is **far more efficient** to cluster the image in superpixels first and operate on those in further steps.
I found a …
-
When I use your code to generate superpixels, I meet the following problem:
![image](https://github.com/Baeksweety/superpixel_transformer/assets/42089575/36524dc7-d870-4b79-b31e-f165522ec1bf)
I use …
-
I have tried it for some medical images which are a bit larger than standard computer vision images and then the processing takes significantly longer time and on the other hand, setting larger step m…
Borda updated
5 years ago
-
There is a desire for a new view (or perhaps an enhancement to an existing view) that allows for review of many superpixels at once.
**Potential capabilities:**
1. Ability to view several superpi…
-
Add an imputer that works for images. This imputer should automatically detect superpixels in the image and use these as players for the approximators.
-
Hello, thanks for the amazing work you've done!
I've read the released code and I noticed that there are no superpixel number information in the proprocess code for SAM related to semantic segmentati…
-
Thank you for sharing your work. I have a question about the overlap folder. How do you generate the overlaps between superpixels and save it in the coverage_superpixel folder? Thanks.