This webpage contains qualitative result of our model for a given image with a query pixel location. The table below contains 6 columns displaying the input with query pixel annotated with a red square, material label along with red square marked on the selection, ground truth mask, followed by results from our model, scores predicted by our model, and then output of our model further refined using KNN-Matting. Please zoom out to see all results in a single pane. We strongly recommend zooming out to 50% to see most results in the same pane.
|Input||Material Label||Ground Truth||(Ours) DINO ViT8 backbone||(Ours) DINO ViT8 Scores||(Ours) DINO ViT8 backbone, refined with KNN-Matting|