Closed jones873 closed 1 month ago
@jones873 This is a failure of the foreground segmentation model - the images you shared are out of distribution of our segmentation labels.
To resolve this, we have added a "no-bg-removal" option to Background Removal Model. This will visualize the depth/normal prediction for the entire image. Note, our models are supervised only on human pixels.
Results on your images below:
@jones873 This is a failure of the foreground segmentation model - the images you shared are out of distribution of our segmentation labels.
To resolve this, we have added a "no-bg-removal" option to Background Removal Model. This will visualize the depth/normal prediction for the entire image. Note, our models are supervised only on human pixels.
Results on your images below:
hi @rawalkhirodkar then may i ask why not to use a person detector like detectron2/yolox to replace sensitive segmentation? just like what is performed for topdown pose est. thx & best,
Tried again with the new update, the same problem occurs, and on the bas-relief image nothing was produced. I cannot believe a company as big as Meta would allow something as bad a this to be put out in the public domain....