This BiRefNet was trained with images in 2048x2048 for higher resolution image matting with transparency. Performance: All tested in FP16 mode. Dataset Method Resolution maxFm wFmeasure MAE Smeasure meanEm HCE maxEm meanFm adpEm adpFm mBA maxBIoU meanBIoU : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : : TE AM 2k BiRefNet HR matting epoch 135 2048x2048 .974 .997 .989 .002 .998 .987 .988 .961 .981 .000 .879 .965 .893 TE P3M 500 NP BiRefNet HR matting epoch 135 2048x2048 .980 .996 .989 .002 .997 .987 .989 .880 .900 .000 .853 .947 .897 TE AM 2k BiRefNet matting epoch 100 1024x1024 .973 .996 .990 .003 .997 .987 .989 .987 .991 .000 .846 .952 .890 TE P3M 500 NP BiRefNet matting epoch 100 1024x1024 .979 .996 .990 .003 .997 .987 .989 .928 .951 .000 .830 .940 .891 TE AM 2k BiRefNet matting epoch 100 2048x2048 .971 .996 .990 .003 .997 .987 .988 .990 .992 .000 .838 .941 .891 TE P3M 500 NP BiRefNet matting epoch 100 2048x2048 .978 .995 .990 .003 .996 .987 .989 .955 .971 .000 .818 .931 .891 Bilateral Reference for High Resolution Dichotomous Image Segmentation Peng Zheng 1,4,5,6 ,  Dehong Gao 2 ,  Deng Ping Fan 1 ,  Li Liu 3 ,  Jorma Laaksonen 4 ,&thins…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy