Submitted by Nikolai Smolyanskiy.

Submission data

Full nameNVStereoNet: An Efficient Semi-Supervised Deep Neural Network Approach
DescriptionWe propose a novel semi-supervised learning approach to training a deep stereo neural network, along with a novel architecture
containing a machine-learned argmax layer and a custom, publicly available runtime that enables a smaller version of our stereo DNN to run on an
embedded GPU.
Publication titleOn the Importance of Stereo for Accurate Depth Estimation: An Efficient Semi-Supervised Deep Neural Network Approach
Publication authorsNikolai Smolyanskiy, Alexey Kamenev, Stan Birchfield
Publication venueArxiv
Publication URL
Programming language(s)TensorFlow
HardwareTitan XP
Submission creation date1 Jun, 2018
Last edited1 Jun, 2018

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 views16.046.7512.906.377.4212.899.7422.7825.1230.3246.1934.3725.3821.4821.385.943.106.0710.094.018.54

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.