Submitted by Gengshan Yang.

Submission data

Full nameHierarchical Deep Stereo Matching on High- Resolution Images
DescriptionAn end-to-end framework that searches for
correspondences incrementally over a coarse-to-fine
hierarchy designed for high-resolution stereo
Parameters- Middlebury model ran at 3.2X original ETH3D resolution;
- max_disparity set to 320px (before upsampling)
Publication titleHierarchical Deep Stereo Matching on High-resolution Images
Publication authorsGengshan Yang, Joshua Manela, Michael Happold, and Deva Ramanan
Publication venueCVPR 2019
Publication URL
Programming language(s)Python
Source code or download URL
Submission creation date12 Aug, 2020
Last edited14 Aug, 2020

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
permissivetwo views4.200.322.760.630.696.951.6911.968.368.8312.1715.184.216.913.300.

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.