Submitted by Dominik Hirner.

Submission data

Full nameFully-convolutional deformable similarity network with depth completion
Publication titleFCDSN-DC: An accurate but lightweight end-to-end trainable neural network for stereo estimation with depth completion
Publication authorsDominik Hirner, Friedrich Fraundorfer
Programming language(s)python
HardwareGeforce RTX 2080 TI
Submission creation date17 Dec, 2021
Last edited17 Dec, 2021

High-res multi-view results

multi-view co.statueterrac.
No results yet.

Low-res many-view results

indooroutdoorlakesidesand boxstorage roomstorage room 2tunnel
No results yet.

Low-res two-view results

Infoalllakes. 1llakes. 1ssand box 1lsand box 1sstora. room 1lstora. room 1sstora. room 2lstora. room 2sstora. room 2 1lstora. room 2 1sstora. room 2 2lstora. room 2 2sstora. room 3lstora. room 3stunnel 1ltunnel 1stunnel 2ltunnel 2stunnel 3ltunnel 3s
two views10.240.563.491.961.2916.904.5917.1619.1024.6432.4633.8222.1415.9310.450.

SLAM results

allboxesboxes darkbuddhacables 4cables 5desk 1desk 2desk changing 2desk dark 1desk dark 2desk global light changesdesk ir lightdinodroneforeground occlusionhelmetkidnap 2lamplarge loop 2large loop 3large non loopmotion 2motion 3motion 4planar 1reflective 2scale changetable 1table 2table 5table 6table global light changestable local light changestable scenetrashbin
No results yet.