+
−
⇧
i
D
T
forest (low-res many-view) - Tolerance 5cm
Ground Truth (full)
Ground Truth (rig eval)
3Dnovator
3Dnovator - accuracy (89.31%)
3Dnovator - completeness (77.54%)
3Dnovator+
3Dnovator+ - accuracy (87.65%)
3Dnovator+ - completeness (79.28%)
A-TVSNet + Gipuma
A-TVSNet + Gipuma - accuracy (69.03%)
A-TVSNet + Gipuma - completeness (80.67%)
ACMH
ACMH - accuracy (69.08%)
ACMH - completeness (82.90%)
ACMH+
ACMH+ - accuracy (66.29%)
ACMH+ - completeness (83.87%)
ACMM
ACMM - accuracy (67.95%)
ACMM - completeness (82.64%)
ACMP
ACMP - accuracy (65.89%)
ACMP - completeness (82.56%)
BP-MVSNet
BP-MVSNet - accuracy (78.54%)
BP-MVSNet - completeness (75.71%)
CasMVSNet(base)
CasMVSNet(base) - accuracy (91.97%)
CasMVSNet(base) - completeness (66.45%)
CasMVSNet(SR_A)
CasMVSNet(SR_A) - accuracy (98.17%)
CasMVSNet(SR_A) - completeness (49.81%)
CasMVSNet(SR_B)
CasMVSNet(SR_B) - accuracy (89.97%)
CasMVSNet(SR_B) - completeness (68.72%)
CIDER
CIDER - accuracy (79.88%)
CIDER - completeness (77.68%)
CMPMVS
CMPMVS - accuracy (2.70%)
CMPMVS - completeness (0.15%)
COLMAP(base)
COLMAP(base) - accuracy (70.33%)
COLMAP(base) - completeness (84.56%)
COLMAP(SR)
COLMAP(SR) - accuracy (70.92%)
COLMAP(SR) - completeness (88.95%)
COLMAP_ROB
COLMAP_ROB - accuracy (79.13%)
COLMAP_ROB - completeness (76.99%)
DeepC-MVS
DeepC-MVS - accuracy (78.25%)
DeepC-MVS - completeness (81.64%)
DeepC-MVS_fast
DeepC-MVS_fast - accuracy (80.75%)
DeepC-MVS_fast - completeness (84.63%)
DeepPCF-MVS
DeepPCF-MVS - accuracy (78.24%)
DeepPCF-MVS - completeness (84.87%)
dnet
dnet - accuracy (0.00%)
dnet - completeness (0.00%)
DPSNet
DPSNet - accuracy (40.08%)
DPSNet - completeness (41.95%)
example
example - accuracy (41.30%)
example - completeness (45.65%)
GSE
GSE - accuracy (68.26%)
GSE - completeness (82.85%)
hgnet
hgnet - accuracy (40.08%)
hgnet - completeness (41.95%)
IB-MVS
IB-MVS - accuracy (85.82%)
IB-MVS - completeness (76.01%)
LPCS
LPCS - accuracy (70.27%)
LPCS - completeness (78.22%)
LTVRE_ROB
LTVRE_ROB - accuracy (92.55%)
LTVRE_ROB - completeness (71.12%)
MVE
MVE - accuracy (13.85%)
MVE - completeness (38.03%)
OpenMVS
OpenMVS - accuracy (84.12%)
OpenMVS - completeness (75.83%)
PCF-MVS
PCF-MVS - accuracy (79.84%)
PCF-MVS - completeness (86.62%)
PLC
PLC - accuracy (66.38%)
PLC - completeness (84.71%)
PMVS
PMVS - accuracy (79.04%)
PMVS - completeness (35.44%)
TAPA-MVS
TAPA-MVS - accuracy (77.54%)
TAPA-MVS - completeness (80.76%)
TAPA-MVS(SR)
TAPA-MVS(SR) - accuracy (79.11%)
TAPA-MVS(SR) - completeness (82.49%)
unsupervisedMVS_cas
unsupervisedMVS_cas - accuracy (49.03%)
unsupervisedMVS_cas - completeness (61.57%)
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