Submitted by Trang Quynh.

Submission data

Full nameCurvature-guided Dynamic Scale Multi-view Stereo Network
DescriptionUsing normal curvature to enhance the matching cost volume.
ParametersNumber sweeping planes: 256
Publication titleCurvature-guided dynamic scale networks for Multi-view Stereo
Publication authorsKhang Truong Giang, Soohwan Song, Sungho Jo
Publication venueICLR 2022
Publication URLhttps://arxiv.org/pdf/2112.05999.pdf
Programming language(s)Python
HardwareTesla V100
Websitehttps://github.com/TruongKhang/cds-mvsnet
Submission creation date21 Sep, 2021
Last edited19 Apr, 2022

High-res multi-view results



Infoallhigh-res
multi-view
indooroutdoorbotani.boulde.bridgedoorexhibi.lectur.living.loungeobserv.old co.statueterrac.
79.0777.7083.1787.6068.2384.4086.2067.4976.3686.5461.5490.7961.8687.3390.49

Low-res many-view results



Infoalllow-res
many-view
indooroutdoorlakesidesand boxstorage roomstorage room 2tunnel
No results yet.

Low-res two-view results



Infoalldeliv. area 1ldeliv. area 1sdeliv. area 2ldeliv. area 2sdeliv. area 3ldeliv. area 3select. 1lelect. 1select. 2lelect. 2select. 3lelect. 3sfacade 1sforest 1sforest 2splayg. 1lplayg. 1splayg. 2lplayg. 2splayg. 3lplayg. 3sterra. 1sterra. 2sterra. 1lterra. 1sterra. 2lterra. 2s
No results yet.

SLAM results



allcables 1cables 2cables 3camera shake 1camera shake 2camera shake 3ceiling 1ceiling 2desk 3desk changing 1einstein 1einstein 2einstein darkeinstein flashlighteinstein global light changes 1einstein global light changes 2einstein global light changes 3kidnap 1kidnap darklarge loop 1mannequin 1mannequin 3mannequin 4mannequin 5mannequin 7mannequin face 1mannequin face 2mannequin face 3mannequin headmotion 1planar 2planar 3plant 1plant 2plant 3plant 4plant 5plant darkplant scene 1plant scene 2plant scene 3reflective 1repetitivesfm benchsfm gardensfm house loopsfm lab room 1sfm lab room 2sofa 1sofa 2sofa 3sofa 4sofa dark 1sofa dark 2sofa dark 3sofa shaketable 3table 4table 7vicon light 1vicon light 2
MethodInfo
No results yet.