The 2D semantic instance prediction task involves detecting and segmenting the object in an image.

Evaluation and metrics

Our evaluation ranks all methods according to the average precision for each class. We report the mean average precision AP (from overlaps [0.5:0.95:0.05]), as well as AP 50% for an overlap value of 50. Note that multiple predictions of the same ground truth instance are penalized as false positives.



This table lists the benchmark results for the 2D semantic instance scenario.




Method Infoavg apbathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sort bysort bysort bysort bysorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
EMSANet (Instance)0.241 10.401 10.439 10.085 10.242 10.220 10.081 10.289 20.117 20.121 10.182 10.126 10.346 10.181 20.181 20.358 10.156 10.675 20.131 1
Seichter, Daniel and Fischedick, Söhnke and Köhler, Mona and Gross, Horst-Michael: EMSANet: Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments. IJCNN 2022
FKNet0.204 30.334 30.358 20.038 20.234 20.184 20.025 30.318 10.042 40.088 20.141 20.053 40.300 30.207 10.171 30.292 20.149 20.636 30.109 2
UniDet_RVC0.205 20.381 20.323 30.037 30.226 30.177 30.063 20.277 30.120 10.067 30.131 30.074 30.317 20.080 30.235 10.289 30.141 30.678 10.080 3
MaskRCNN_ScanNetpermissive0.119 40.129 40.212 40.002 40.112 40.148 40.014 40.205 40.044 30.066 40.078 40.095 20.142 40.030 40.128 40.139 40.080 40.459 40.057 4
Re-implementation of Kaiming He, Georgia Gkioxari, Piotr Dollár, Ross Girshick: Mask R-CNN. ICCV'17