+
−
⇧
i
D
T
terrains (low-res many-view) - Tolerance 1cm
Ground Truth (full)
Ground Truth (rig eval)
3Dnovator
3Dnovator - accuracy (86.71%)
3Dnovator - completeness (57.54%)
3Dnovator+
3Dnovator+ - accuracy (85.20%)
3Dnovator+ - completeness (56.56%)
A-TVSNet + Gipuma
A-TVSNet + Gipuma - accuracy (68.90%)
A-TVSNet + Gipuma - completeness (46.49%)
ACMH
ACMH - accuracy (60.86%)
ACMH - completeness (54.44%)
ACMH+
ACMH+ - accuracy (61.78%)
ACMH+ - completeness (57.76%)
ACMM
ACMM - accuracy (67.15%)
ACMM - completeness (59.20%)
ACMP
ACMP - accuracy (66.02%)
ACMP - completeness (60.67%)
BP-MVSNet
BP-MVSNet - accuracy (60.77%)
BP-MVSNet - completeness (55.56%)
CasMVSNet(base)
CasMVSNet(base) - accuracy (60.16%)
CasMVSNet(base) - completeness (44.27%)
CasMVSNet(SR_A)
CasMVSNet(SR_A) - accuracy (68.52%)
CasMVSNet(SR_A) - completeness (45.21%)
CasMVSNet(SR_B)
CasMVSNet(SR_B) - accuracy (68.52%)
CasMVSNet(SR_B) - completeness (45.21%)
CIDER
CIDER - accuracy (63.67%)
CIDER - completeness (34.49%)
CMPMVS
CMPMVS - accuracy (59.24%)
CMPMVS - completeness (28.38%)
COLMAP(base)
COLMAP(base) - accuracy (62.27%)
COLMAP(base) - completeness (55.12%)
COLMAP(SR)
COLMAP(SR) - accuracy (63.01%)
COLMAP(SR) - completeness (53.42%)
COLMAP_ROB
COLMAP_ROB - accuracy (80.23%)
COLMAP_ROB - completeness (46.61%)
DeepC-MVS
DeepC-MVS - accuracy (77.07%)
DeepC-MVS - completeness (62.65%)
DeepC-MVS_fast
DeepC-MVS_fast - accuracy (78.84%)
DeepC-MVS_fast - completeness (59.38%)
DeepPCF-MVS
DeepPCF-MVS - accuracy (77.58%)
DeepPCF-MVS - completeness (67.63%)
dnet
dnet - accuracy (0.00%)
dnet - completeness (0.00%)
DPSNet
DPSNet - accuracy (43.77%)
DPSNet - completeness (19.73%)
example
example - accuracy (42.17%)
example - completeness (30.52%)
GSE
GSE - accuracy (66.03%)
GSE - completeness (46.40%)
hgnet
hgnet - accuracy (43.77%)
hgnet - completeness (19.73%)
IB-MVS
IB-MVS - accuracy (79.65%)
IB-MVS - completeness (54.14%)
LPCS
LPCS - accuracy (59.29%)
LPCS - completeness (46.40%)
LTVRE_ROB
LTVRE_ROB - accuracy (87.66%)
LTVRE_ROB - completeness (53.60%)
MVE
MVE - accuracy (20.50%)
MVE - completeness (38.02%)
OpenMVS
OpenMVS - accuracy (84.04%)
OpenMVS - completeness (55.52%)
PCF-MVS
PCF-MVS - accuracy (67.50%)
PCF-MVS - completeness (59.66%)
PLC
PLC - accuracy (61.59%)
PLC - completeness (56.45%)
PMVS
PMVS - accuracy (77.16%)
PMVS - completeness (34.52%)
TAPA-MVS
TAPA-MVS - accuracy (73.04%)
TAPA-MVS - completeness (63.09%)
TAPA-MVS(SR)
TAPA-MVS(SR) - accuracy (69.00%)
TAPA-MVS(SR) - completeness (55.25%)
unsupervisedMVS_cas
unsupervisedMVS_cas - accuracy (24.25%)
unsupervisedMVS_cas - completeness (40.47%)
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