Submitted by JUNHONG MIN.

Submission data

Full nameConfidence-Aware Symmetric Stereo Matching via U-Net Transformer
Descriptionwe propose a novel deep stereo matching network a new real-world stereo dataset of cluttered objects taken with a commercially available stereo sensor. We design a U-shaped architecture with various types of attentions which more efficiently extracts global and local contexts from rectified image pairs, resulting in highly accurate disparities. Furthermore, its symmetric structure allows simultaneous estimation both left and right disparity. It can also implicitly estimate the uncertainty i.e. the confidence of estimated disparities.
Parametersfeature dimension 128:
4-level U-net for the feature extraction
3-level U-net for the refinement
processing at 1536x1024 pixel scale
Publication titleConfidence-Aware Symmetric Stereo Matching via U-Net Transformer
Publication authorsJunhong Min, Youngpil Jeon
Programming language(s)Python
Hardwarei9-13900k, Nvidia RTX 4090
Submission creation date14 Sep, 2023
Last edited14 Sep, 2023

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 views2.440.443.560.850.383.140.229.644.006.787.623.573.583.801.

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.