+
−
⇧
i
D
T
delivery_area (low-res many-view) - Tolerance 5cm
Ground Truth (full)
Ground Truth (rig eval)
3Dnovator
3Dnovator - accuracy (79.50%)
3Dnovator - completeness (53.83%)
3Dnovator+
3Dnovator+ - accuracy (80.14%)
3Dnovator+ - completeness (55.47%)
A-TVSNet + Gipuma
A-TVSNet + Gipuma - accuracy (44.42%)
A-TVSNet + Gipuma - completeness (61.29%)
ACMH
ACMH - accuracy (62.85%)
ACMH - completeness (61.81%)
ACMH+
ACMH+ - accuracy (65.40%)
ACMH+ - completeness (69.87%)
ACMM
ACMM - accuracy (58.22%)
ACMM - completeness (64.11%)
ACMP
ACMP - accuracy (64.49%)
ACMP - completeness (71.36%)
BP-MVSNet
BP-MVSNet - accuracy (58.92%)
BP-MVSNet - completeness (63.04%)
CasMVSNet(base)
CasMVSNet(base) - accuracy (66.17%)
CasMVSNet(base) - completeness (39.87%)
CasMVSNet(SR_A)
CasMVSNet(SR_A) - accuracy (60.20%)
CasMVSNet(SR_A) - completeness (40.21%)
CasMVSNet(SR_B)
CasMVSNet(SR_B) - accuracy (60.20%)
CasMVSNet(SR_B) - completeness (40.21%)
CIDER
CIDER - accuracy (47.18%)
CIDER - completeness (58.29%)
CMPMVS
CMPMVS - accuracy (0.00%)
CMPMVS - completeness (0.00%)
COLMAP(base)
COLMAP(base) - accuracy (69.03%)
COLMAP(base) - completeness (69.37%)
COLMAP(SR)
COLMAP(SR) - accuracy (64.78%)
COLMAP(SR) - completeness (72.76%)
COLMAP_ROB
COLMAP_ROB - accuracy (78.00%)
COLMAP_ROB - completeness (53.13%)
DeepC-MVS
DeepC-MVS - accuracy (74.27%)
DeepC-MVS - completeness (72.70%)
DeepC-MVS_fast
DeepC-MVS_fast - accuracy (77.25%)
DeepC-MVS_fast - completeness (71.55%)
DeepPCF-MVS
DeepPCF-MVS - accuracy (75.44%)
DeepPCF-MVS - completeness (74.79%)
dnet
dnet - accuracy (0.00%)
dnet - completeness (0.00%)
DPSNet
DPSNet - accuracy (10.07%)
DPSNet - completeness (25.58%)
example
example - accuracy (11.95%)
example - completeness (16.24%)
GSE
GSE - accuracy (73.41%)
GSE - completeness (68.49%)
hgnet
hgnet - accuracy (10.07%)
hgnet - completeness (25.58%)
IB-MVS
IB-MVS - accuracy (67.16%)
IB-MVS - completeness (56.43%)
LPCS
LPCS - accuracy (76.84%)
LPCS - completeness (53.87%)
LTVRE_ROB
LTVRE_ROB - accuracy (82.09%)
LTVRE_ROB - completeness (55.01%)
MVE
MVE - accuracy (8.08%)
MVE - completeness (32.82%)
OpenMVS
OpenMVS - accuracy (75.58%)
OpenMVS - completeness (53.66%)
PCF-MVS
PCF-MVS - accuracy (67.71%)
PCF-MVS - completeness (72.95%)
PLC
PLC - accuracy (64.91%)
PLC - completeness (69.95%)
PMVS
PMVS - accuracy (51.80%)
PMVS - completeness (13.72%)
TAPA-MVS
TAPA-MVS - accuracy (55.45%)
TAPA-MVS - completeness (79.31%)
TAPA-MVS(SR)
TAPA-MVS(SR) - accuracy (64.79%)
TAPA-MVS(SR) - completeness (65.58%)
unsupervisedMVS_cas
unsupervisedMVS_cas - accuracy (37.38%)
unsupervisedMVS_cas - completeness (39.10%)
Attributes:
RGB
RGB and Elevation
Elevation
Level of Detail
RGB
Attribute Weights
RGB:
Intensity:
Elevation:
Classification:
Return Number:
Source ID:
RGB
Gamma:
1.00
Brightness:
0.00
Contrast:
0.00
Elevation
:
0.00 to 1.00
Transition
transition:
Intensity
Range:
0 to 300
Gamma:
1.00
Brightness:
0.00
Contrast:
0.00
:
1,000,000
:
1.00
:
60
:
1.00
Point Sizing
Fixed
Attenuated
Adaptive
Adaptive
Squares
Circles
Interpolation
Squares
Eye-Dome-Lighting
:
1.4
:
1.0
Background
Gradient
Black
White
Navigation
:
0.4
Potree
is a viewer for large point cloud / LIDAR data sets, developed at the Vienna University of Technology.
(github)
Author:
Markus Schütz
License:
FreeBSD (2-clause BSD)
Libraries:
three.js
Jquery
laszip
Plas.io (laslaz)
OpenLayers3
proj4js
tween
i18next
Donators:
rapidlasso
georepublic
sitn
Veesus
sigeom sa
Credits:
Michael Wimmer
&
Claus Scheiblauer
TU Wien, Insitute of Computer Graphics and Algorithms
Harvest4D
rapidlasso
georepublic
Howard Butler, Uday Verma, Connor Manning
Cloud Compare
sitn
loading 1 / 10
Fixed
Attenuated
Adaptive
Squares
Circles
Interpolation
RGB
RGB and Elevation
Elevation
Level of Detail