This table lists the benchmark results for the 3D semantic label scenario.


Method Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
3DMV0.443 10.328 10.510 10.418 20.353 10.595 10.252 10.681 10.398 10.365 10.790 10.286 10.215 10.481 10.195 10.371 10.491 10.321 10.669 10.610 10.523 1
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
ScanNetpermissive0.306 20.203 20.366 20.501 10.311 20.524 20.211 20.002 20.342 20.189 20.786 20.145 20.102 20.245 20.152 20.318 20.348 20.300 20.460 20.437 20.182 2
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR'17

This table lists the benchmark results for the 3D semantic instance scenario.




Method Infoavg ap 25%bathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
MaskRCNN 2d->3d Proj0.241 10.724 10.146 10.149 10.189 10.167 10.141 10.101 10.169 10.132 10.226 10.368 10.367 10.028 10.554 10.280 10.142 10.440 10.021 1

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


Method Infoavg ioubathtubbedbookshelfcabinetchaircountercurtaindeskdoorfloorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwallwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
3DMV (2d proj)0.453 10.379 10.578 10.290 30.376 10.335 10.296 10.676 10.523 10.395 10.839 10.220 10.281 10.505 10.182 10.452 10.593 10.366 10.689 10.668 20.408 2
Angela Dai, Matthias Niessner: 3DMV: Joint 3D-Multi-View Prediction for 3D Semantic Scene Segmentation. ECCV'18
Enet (reimpl)0.376 20.264 30.452 30.452 20.365 20.181 20.143 30.456 20.409 30.346 20.769 30.164 20.218 20.359 20.123 30.403 30.381 30.313 30.571 20.685 10.472 1
Re-implementation of Adam Paszke, Abhishek Chaurasia, Sangpil Kim, Eugenio Culurciello: ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation.
ScanNet (2d proj)permissive0.330 30.293 20.521 20.657 10.361 30.161 30.250 20.004 30.440 20.183 30.836 20.125 30.060 30.319 30.132 20.417 20.412 20.344 20.541 30.427 30.109 3
Angela Dai, Angel X. Chang, Manolis Savva, Maciej Halber, Thomas Funkhouser, Matthias Nießner: ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes. CVPR

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




Method Infoavg apbathtubbedbookshelfcabinetchaircountercurtaindeskdoorotherfurniturepicturerefrigeratorshower curtainsinksofatabletoiletwindow
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
MaskRCNN_ScanNetpermissive0.111 10.103 10.207 10.010 10.116 10.153 10.016 10.218 10.052 10.039 10.080 10.097 10.136 10.009 10.131 10.094 10.077 10.415 10.041 1
Re-implementation of Kaiming He, Georgia Gkioxari, Piotr Dollár, Ross Girshick: Mask R-CNN. ICCV

This table lists the benchmark results for the scene type classification scenario.


Method Infoavg iouapartmentbathroombedroom / hotelbookstore / libraryconference roomcopy/mail roomhallwaykitchenlaundry roomliving room / loungemiscofficestorage / basement / garage
sorted bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort bysort by
No results yet.